CS 1675 PPG Final Project
Sameera Boppana
3/26/2022
Load Packages
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.5 ✓ purrr 0.3.4
## ✓ tibble 3.1.6 ✓ dplyr 1.0.8
## ✓ tidyr 1.2.0 ✓ stringr 1.4.0
## ✓ readr 2.1.2 ✓ forcats 0.5.1## Warning: package 'tidyr' was built under R version 4.0.5## Warning: package 'readr' was built under R version 4.0.5## Warning: package 'dplyr' was built under R version 4.0.5## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(caret)## Loading required package: lattice##
## Attaching package: 'caret'## The following object is masked from 'package:purrr':
##
## liftPart 1: Exploratory Data Analysis
Read Data
Read in the data from CSV file
df <- readr::read_csv('final_project_train.csv', col_names = TRUE)## Rows: 677 Columns: 38
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): region, customer, outcome
## dbl (35): rowid, xb_01, xb_02, xb_03, xn_01, xn_02, xn_03, xa_01, xa_02, xa_...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.df %>% glimpse()## Rows: 677
## Columns: 38
## $ rowid <dbl> 1, 3, 4, 5, 8, 9, 11, 14, 15, 16, 17, 18, 19, 22, 24, 25, 27,…
## $ region <chr> "XX", "XX", "XX", "XX", "XX", "XX", "XX", "XX", "XX", "XX", "…
## $ customer <chr> "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "…
## $ xb_01 <dbl> 4.000000, 1.000000, 2.000000, 2.520000, 2.548387, 3.071429, 3…
## $ xb_02 <dbl> 4, 1, 2, 11, 6, 6, 10, 12, 9, 10, 8, 10, 10, 8, 6, 10, 13, 10…
## $ xb_03 <dbl> 4, 1, 2, -6, -1, 1, -4, -4, -2, -4, -2, -2, -2, -4, 1, -4, -3…
## $ xn_01 <dbl> 3.0000000, 2.0000000, 2.0000000, 1.5333333, 0.8387097, 1.8571…
## $ xn_02 <dbl> 3, 2, 4, 9, 3, 8, 6, 10, 10, 4, 6, 8, 9, 5, 7, 12, 12, 6, 6, …
## $ xn_03 <dbl> 3, 2, 0, -3, -4, -2, -5, -6, -3, -5, -3, -6, -4, -3, 0, -5, -…
## $ xa_01 <dbl> 12.000000, 3.000000, 9.000000, 7.080000, 6.451613, 6.857143, …
## $ xa_02 <dbl> 12, 3, 9, 29, 17, 18, 24, 27, 20, 19, 15, 24, 24, 15, 14, 26,…
## $ xa_03 <dbl> 12, 3, 9, -7, -2, 2, -9, -5, -3, -3, -1, 1, -2, -3, 3, -4, -5…
## $ xb_04 <dbl> 1.3333333, 1.0000000, 1.0000000, 0.8950476, 1.2247312, 1.1857…
## $ xb_05 <dbl> 1.3333333, 1.0000000, 1.0000000, -2.0000000, -0.5000000, 0.00…
## $ xb_06 <dbl> 1.333333, 1.000000, 1.000000, 4.000000, 4.000000, 3.000000, 6…
## $ xb_07 <dbl> 4.000000, 1.000000, 2.000000, 1.933333, 1.967742, 1.714286, 1…
## $ xb_08 <dbl> -1.00000000, 1.00000000, 0.00000000, -0.08000000, 0.35483871,…
## $ xn_04 <dbl> 1.0000000, 2.0000000, 1.0000000, 0.5268889, 0.4688172, 0.5607…
## $ xn_05 <dbl> 1.0000000, 2.0000000, 0.0000000, -1.0000000, -1.3333333, -1.0…
## $ xn_06 <dbl> 1.0, 2.0, 2.0, 2.5, 3.0, 2.0, 4.0, 4.0, 3.0, 2.0, 2.0, 2.5, 2…
## $ xn_07 <dbl> 3.000000, 2.000000, 2.500000, 1.493333, 1.225806, 1.642857, 1…
## $ xn_08 <dbl> -1.0000000, 2.0000000, -1.0000000, -0.4400000, -0.4516129, -0…
## $ xa_04 <dbl> 6.000000, 3.000000, 6.750000, 2.425333, 3.023656, 2.685714, 2…
## $ xa_05 <dbl> 6.0000000, 3.0000000, 4.5000000, -3.5000000, -0.6666667, 0.40…
## $ xa_06 <dbl> 6.000000, 3.000000, 9.000000, 9.000000, 13.000000, 6.000000, …
## $ xa_07 <dbl> 9.000000, 3.000000, 7.500000, 4.466667, 4.612903, 4.071429, 4…
## $ xa_08 <dbl> 3.0000000, 3.0000000, 6.0000000, 0.7066667, 1.3225806, 1.3571…
## $ xw_01 <dbl> 23.00000, 17.00000, 52.50000, 64.52564, 54.75758, 58.33333, 6…
## $ xw_02 <dbl> 23, 17, 48, 0, 12, 15, 0, 0, 0, 7, 14, 0, 0, 0, 8, 8, 0, 4, 2…
## $ xw_03 <dbl> 23, 17, 57, 106, 105, 101, 107, 109, 109, 104, 109, 99, 103, …
## $ xs_01 <dbl> 0.262073307, 0.330804757, 0.239795763, 0.142106837, 0.2442957…
## $ xs_02 <dbl> 0.26207331, 0.33080476, 0.19049123, -0.73321509, -0.12204299,…
## $ xs_03 <dbl> 0.2620733, 0.3308048, 0.2891003, 0.5500723, 1.3134719, 0.6540…
## $ xs_04 <dbl> 0.5375576, 0.4286607, 0.3676937, 0.2865445, 0.2375470, 0.2594…
## $ xs_05 <dbl> 0.5375575604, 0.4286607050, 0.2485001680, 0.0000000000, 0.043…
## $ xs_06 <dbl> 0.5375576, 0.4286607, 0.4868872, 0.6357541, 0.4327004, 0.8672…
## $ response <dbl> 2.617991, 1.184632, 2.216626, 2.726715, 1.483323, 2.039279, 1…
## $ outcome <chr> "non_event", "non_event", "event", "non_event", "non_event", …visdat::vis_miss(df)## Warning: `gather_()` was deprecated in tidyr 1.2.0.
## Please use `gather()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.
There are no missing values present in the data.
visdat::vis_dat(df)
The data types present within the data set are either character or numeric.
df %>% purrr::map_dbl(n_distinct)## rowid region customer xb_01 xb_02 xb_03 xn_01 xn_02
## 677 3 9 229 19 21 225 18
## xn_03 xa_01 xa_02 xa_03 xb_04 xb_05 xb_06 xb_07
## 18 257 38 35 364 59 51 181
## xb_08 xn_04 xn_05 xn_06 xn_07 xn_08 xa_04 xa_05
## 187 360 51 47 174 174 411 87
## xa_06 xa_07 xa_08 xw_01 xw_02 xw_03 xs_01 xs_02
## 87 213 212 396 102 103 676 644
## xs_03 xs_04 xs_05 xs_06 response outcome
## 672 676 663 676 677 2There are a wide range of distinct values.
df %>% count(outcome)## # A tibble: 2 × 2
## outcome n
## <chr> <int>
## 1 event 127
## 2 non_event 550df %>% count(region)## # A tibble: 3 × 2
## region n
## <chr> <int>
## 1 XX 161
## 2 YY 222
## 3 ZZ 294df %>% count(customer)## # A tibble: 9 × 2
## customer n
## <chr> <int>
## 1 A 55
## 2 B 52
## 3 D 32
## 4 E 35
## 5 G 113
## 6 K 38
## 7 M 71
## 8 Other 245
## 9 Q 36df %>% count(customer, region)## # A tibble: 15 × 3
## customer region n
## <chr> <chr> <int>
## 1 A ZZ 55
## 2 B XX 27
## 3 B YY 25
## 4 D XX 17
## 5 D YY 15
## 6 E XX 17
## 7 E YY 18
## 8 G XX 23
## 9 G ZZ 90
## 10 K ZZ 38
## 11 M ZZ 71
## 12 Other XX 77
## 13 Other YY 128
## 14 Other ZZ 40
## 15 Q YY 36All A customers are from region ZZ. All K customers are from region ZZ.
Visualizing the relationship between customer and region
df %>%
ggplot(mapping = aes(x = as.factor(customer))) +
geom_bar(mapping = aes(fill = as.factor(region)), position = "dodge") +
theme_bw()
Continous Input Distributions
Examining the distributions of the continous inputs
continuous_vars <- colnames(df)
continuous_vars <- continuous_vars[-1:-3]
continuous_vars <- continuous_vars[-length(continuous_vars)]
continuous_vars <- continuous_vars[-length(continuous_vars)]
continuous_vars## [1] "xb_01" "xb_02" "xb_03" "xn_01" "xn_02" "xn_03" "xa_01" "xa_02" "xa_03"
## [10] "xb_04" "xb_05" "xb_06" "xb_07" "xb_08" "xn_04" "xn_05" "xn_06" "xn_07"
## [19] "xn_08" "xa_04" "xa_05" "xa_06" "xa_07" "xa_08" "xw_01" "xw_02" "xw_03"
## [28] "xs_01" "xs_02" "xs_03" "xs_04" "xs_05" "xs_06"df %>%
select(all_of(continuous_vars)) %>%
tibble::rowid_to_column() %>%
pivot_longer(!c("rowid")) %>%
ggplot(mapping = aes(x = value)) +
geom_histogram(bins = 50) +
facet_wrap(~name, scales = "free") +
theme_bw() +
theme(axis.text.y = element_blank())
Examining the distribution of the continuous inputs filtering by outcome type
Outcome = Event
df %>%
filter(outcome == "event") %>%
select(all_of(continuous_vars)) %>%
tibble::rowid_to_column() %>%
pivot_longer(!c("rowid")) %>%
ggplot(mapping = aes(x = value)) +
geom_histogram(bins = 50) +
facet_wrap(~name, scales = "free") +
theme_bw() +
theme(axis.text.y = element_blank()) 
df %>%
filter(outcome == "event") %>%
select(all_of(continuous_vars)) %>% summary()## xb_01 xb_02 xb_03 xn_01
## Min. :-4.000 Min. :-4.000 Min. :-7.0000 Min. :-4.00000
## 1st Qu.: 1.050 1st Qu.: 2.500 1st Qu.:-1.0000 1st Qu.:-1.00000
## Median : 2.571 Median : 5.000 Median : 0.0000 Median : 0.33333
## Mean : 2.336 Mean : 4.669 Mean : 0.1811 Mean : 0.01976
## 3rd Qu.: 3.400 3rd Qu.: 7.000 3rd Qu.: 1.5000 3rd Qu.: 1.10238
## Max. : 7.000 Max. :14.000 Max. : 7.0000 Max. : 2.33333
## xn_02 xn_03 xa_01 xa_02
## Min. :-4.000 Min. :-6.000 Min. :-3.000 Min. :-3.00
## 1st Qu.:-0.500 1st Qu.:-3.000 1st Qu.: 4.817 1st Qu.: 7.00
## Median : 2.000 Median :-2.000 Median : 6.400 Median :11.00
## Mean : 2.071 Mean :-2.126 Mean : 6.161 Mean :11.17
## 3rd Qu.: 4.000 3rd Qu.:-1.000 3rd Qu.: 8.000 3rd Qu.:15.00
## Max. : 8.000 Max. : 1.000 Max. :16.000 Max. :26.00
## xa_03 xb_04 xb_05 xb_06
## Min. :-7.000 Min. :-2.0000 Min. :-2.0000 Min. :-2.000
## 1st Qu.:-1.000 1st Qu.: 0.5000 1st Qu.:-0.5000 1st Qu.: 1.000
## Median : 2.000 Median : 0.9722 Median : 0.0000 Median : 1.667
## Mean : 1.953 Mean : 0.8315 Mean : 0.0790 Mean : 1.750
## 3rd Qu.: 4.000 3rd Qu.: 1.2069 3rd Qu.: 0.6333 3rd Qu.: 2.500
## Max. :16.000 Max. : 2.3333 Max. : 2.3333 Max. : 6.000
## xb_07 xb_08 xn_04 xn_05
## Min. :-1.000 Min. :-4.0000 Min. :-4.00000 Min. :-4.0000
## 1st Qu.: 1.396 1st Qu.:-0.7667 1st Qu.:-0.35417 1st Qu.:-1.0000
## Median : 1.812 Median : 0.0000 Median : 0.12500 Median :-1.0000
## Mean : 1.794 Mean :-0.1639 Mean :-0.01121 Mean :-0.8656
## 3rd Qu.: 2.099 3rd Qu.: 0.3661 3rd Qu.: 0.44097 3rd Qu.:-0.3667
## Max. : 5.000 Max. : 2.0000 Max. : 1.00000 Max. : 0.5000
## xn_06 xn_07 xn_08 xa_04
## Min. :-4.0000 Min. :-4.0000 Min. :-4.0000 Min. :-2.000
## 1st Qu.:-0.1000 1st Qu.: 0.8333 1st Qu.:-1.1944 1st Qu.: 1.736
## Median : 1.0000 Median : 1.0000 Median :-0.8000 Median : 2.581
## Mean : 0.8053 Mean : 0.8639 Mean :-0.9634 Mean : 2.375
## 3rd Qu.: 1.7083 3rd Qu.: 1.3333 3rd Qu.:-0.3632 3rd Qu.: 3.099
## Max. : 4.0000 Max. : 2.5000 Max. : 0.5000 Max. : 6.750
## xa_05 xa_06 xa_07 xa_08
## Min. :-6.0000 Min. :-2.000 Min. :-2.000 Min. :-5.0000
## 1st Qu.:-0.2917 1st Qu.: 2.875 1st Qu.: 3.500 1st Qu.:-0.5000
## Median : 0.6667 Median : 4.000 Median : 4.088 Median : 0.7500
## Mean : 0.7251 Mean : 4.464 Mean : 4.215 Mean : 0.5234
## 3rd Qu.: 1.8286 3rd Qu.: 6.000 3rd Qu.: 5.000 3rd Qu.: 1.6753
## Max. : 6.0000 Max. :15.000 Max. :11.000 Max. : 6.0000
## xw_01 xw_02 xw_03 xs_01
## Min. : 14.00 Min. : 0.00 Min. : 14.0 Min. :-0.2177
## 1st Qu.: 43.85 1st Qu.: 10.50 1st Qu.: 65.5 1st Qu.: 0.1073
## Median : 56.85 Median : 25.00 Median : 94.0 Median : 0.1715
## Mean : 57.59 Mean : 30.93 Mean : 82.1 Mean : 0.1660
## 3rd Qu.: 68.69 3rd Qu.: 45.00 3rd Qu.:101.0 3rd Qu.: 0.2250
## Max. :102.00 Max. :102.00 Max. :110.0 Max. : 0.5247
## xs_02 xs_03 xs_04 xs_05
## Min. :-0.43347 Min. :-0.2177 Min. :0.0000 Min. :0.00000
## 1st Qu.:-0.14100 1st Qu.: 0.1759 1st Qu.:0.2455 1st Qu.:0.08714
## Median : 0.00000 Median : 0.3402 Median :0.2859 Median :0.15195
## Mean :-0.01581 Mean : 0.3603 Mean :0.3103 Mean :0.18920
## 3rd Qu.: 0.12984 3rd Qu.: 0.4968 3rd Qu.:0.3501 3rd Qu.:0.26305
## Max. : 0.52468 Max. : 1.1833 Max. :0.8988 Max. :0.89883
## xs_06
## Min. :0.0000
## 1st Qu.:0.3334
## Median :0.4727
## Mean :0.4815
## 3rd Qu.:0.5708
## Max. :1.2703Outcome = Non_Event
df %>%
filter(outcome == "non_event") %>%
select(all_of(continuous_vars)) %>%
tibble::rowid_to_column() %>%
pivot_longer(!c("rowid")) %>%
ggplot(mapping = aes(x = value)) +
geom_histogram(bins = 50) +
facet_wrap(~name, scales = "free") +
theme_bw() +
theme(axis.text.y = element_blank())
df %>%
filter(outcome == "non_event") %>%
select(all_of(continuous_vars)) %>%
summary()## xb_01 xb_02 xb_03 xn_01
## Min. :-2.000 Min. :-2.000 Min. :-6.000 Min. :-3.500
## 1st Qu.: 2.667 1st Qu.: 4.000 1st Qu.:-1.000 1st Qu.: 1.000
## Median : 3.429 Median : 6.000 Median : 1.000 Median : 1.857
## Mean : 3.618 Mean : 5.998 Mean : 1.456 Mean : 1.913
## 3rd Qu.: 4.500 3rd Qu.: 8.000 3rd Qu.: 3.000 3rd Qu.: 2.650
## Max. :14.000 Max. :15.000 Max. :14.000 Max. :10.000
## xn_02 xn_03 xa_01 xa_02
## Min. :-3.000 Min. :-7.000000 Min. :-2.000 Min. :-2.00
## 1st Qu.: 2.000 1st Qu.:-2.000000 1st Qu.: 6.500 1st Qu.: 8.25
## Median : 4.000 Median : 0.000000 Median : 8.156 Median :13.50
## Mean : 4.033 Mean :-0.003636 Mean : 8.515 Mean :13.72
## 3rd Qu.: 6.000 3rd Qu.: 2.000000 3rd Qu.:10.036 3rd Qu.:18.00
## Max. :13.000 Max. :10.000000 Max. :35.000 Max. :38.00
## xa_03 xb_04 xb_05 xb_06
## Min. :-9.000 Min. :-1.0000 Min. :-3.0000 Min. :-1.000
## 1st Qu.: 0.000 1st Qu.: 0.9383 1st Qu.:-0.2500 1st Qu.: 1.250
## Median : 4.000 Median : 1.1974 Median : 0.5000 Median : 2.000
## Mean : 4.271 Mean : 1.2273 Mean : 0.4839 Mean : 2.189
## 3rd Qu.: 7.000 3rd Qu.: 1.5000 3rd Qu.: 1.0000 3rd Qu.: 3.000
## Max. :35.000 Max. : 5.0000 Max. : 5.0000 Max. : 9.000
## xb_07 xb_08 xn_04 xn_05
## Min. :-1.000 Min. :-2.0000 Min. :-1.0000 Min. :-3.000000
## 1st Qu.: 1.802 1st Qu.:-0.1667 1st Qu.: 0.4333 1st Qu.:-1.000000
## Median : 2.000 Median : 0.2824 Median : 0.6752 Median : 0.000000
## Mean : 2.167 Mean : 0.2993 Mean : 0.7458 Mean : 0.004892
## 3rd Qu.: 2.500 3rd Qu.: 1.0000 3rd Qu.: 1.0000 3rd Qu.: 0.750000
## Max. : 7.000 Max. : 5.0000 Max. : 5.0000 Max. : 5.000000
## xn_06 xn_07 xn_08 xa_04
## Min. :-1.000 Min. :-1.000 Min. :-3.0000 Min. :-2.000
## 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.:-0.6667 1st Qu.: 2.388
## Median : 1.367 Median : 1.500 Median :-0.1854 Median : 3.000
## Mean : 1.634 Mean : 1.532 Mean :-0.1063 Mean : 3.076
## 3rd Qu.: 2.000 3rd Qu.: 2.000 3rd Qu.: 0.3333 3rd Qu.: 3.577
## Max. : 7.000 Max. : 5.000 Max. : 5.0000 Max. :12.000
## xa_05 xa_06 xa_07 xa_08
## Min. :-8.00000 Min. :-2.000 Min. :-2.000 Min. :-5.0000
## 1st Qu.: 0.04167 1st Qu.: 3.000 1st Qu.: 4.000 1st Qu.: 0.6254
## Median : 1.50000 Median : 4.500 Median : 4.718 Median : 1.2386
## Mean : 1.53068 Mean : 5.308 Mean : 4.810 Mean : 1.3823
## 3rd Qu.: 3.00000 3rd Qu.: 7.000 3rd Qu.: 5.500 3rd Qu.: 2.0000
## Max. :12.00000 Max. :23.000 Max. :13.000 Max. :12.0000
## xw_01 xw_02 xw_03 xs_01
## Min. : 9.00 Min. : 0.00 Min. : 9.00 Min. :-0.3612
## 1st Qu.: 44.50 1st Qu.: 9.00 1st Qu.: 57.00 1st Qu.: 0.1589
## Median : 57.79 Median : 24.00 Median : 91.50 Median : 0.2254
## Mean : 56.88 Mean : 32.08 Mean : 78.37 Mean : 0.2261
## 3rd Qu.: 67.46 3rd Qu.: 51.00 3rd Qu.:101.00 3rd Qu.: 0.2945
## Max. :108.00 Max. :108.00 Max. :113.00 Max. : 0.7548
## xs_02 xs_03 xs_04 xs_05
## Min. :-0.89585 Min. :-0.3612 Min. :0.02511 Min. :0.00000
## 1st Qu.:-0.14308 1st Qu.: 0.2578 1st Qu.:0.24250 1st Qu.:0.07771
## Median : 0.04786 Median : 0.3976 Median :0.29147 Median :0.16581
## Mean : 0.03107 Mean : 0.4388 Mean :0.29900 Mean :0.18850
## 3rd Qu.: 0.22046 3rd Qu.: 0.6097 3rd Qu.:0.34113 3rd Qu.:0.26384
## Max. : 0.69105 Max. : 1.7907 Max. :0.68960 Max. :0.68960
## xs_06
## Min. :0.02511
## 1st Qu.:0.29971
## Median :0.42122
## Mean :0.46320
## 3rd Qu.:0.60198
## Max. :1.30883For most of the sentiment derived features, each product sold to a customer has a greater sentiment value when the outcome is classified as an event.
Examining the impact on region on the continuous variables
Region = XX
df %>%
filter(region == "XX") %>%
select(all_of(continuous_vars)) %>%
tibble::rowid_to_column() %>%
pivot_longer(!c("rowid")) %>%
ggplot(mapping = aes(x = value)) +
geom_histogram(bins = 50) +
facet_wrap(~name, scales = "free") +
theme_bw() +
theme(axis.text.y = element_blank())
df %>%
filter(region == "XX") %>%
select(all_of(continuous_vars)) %>%
summary()## xb_01 xb_02 xb_03 xn_01
## Min. :-1.000 Min. :-1.000 Min. :-6.0000 Min. :-2.500
## 1st Qu.: 2.625 1st Qu.: 4.000 1st Qu.:-2.0000 1st Qu.: 1.000
## Median : 3.250 Median : 7.000 Median : 0.0000 Median : 1.667
## Mean : 3.354 Mean : 6.708 Mean : 0.3851 Mean : 1.588
## 3rd Qu.: 4.000 3rd Qu.: 9.000 3rd Qu.: 2.0000 3rd Qu.: 2.286
## Max. :12.000 Max. :15.000 Max. :12.0000 Max. :10.000
## xn_02 xn_03 xa_01 xa_02
## Min. :-2.000 Min. :-6.000 Min. :-2.000 Min. :-2.00
## 1st Qu.: 2.000 1st Qu.:-3.000 1st Qu.: 6.677 1st Qu.:11.00
## Median : 4.000 Median :-1.000 Median : 8.000 Median :15.00
## Mean : 4.621 Mean :-1.087 Mean : 8.093 Mean :15.26
## 3rd Qu.: 6.000 3rd Qu.: 0.000 3rd Qu.: 9.667 3rd Qu.:21.00
## Max. :12.000 Max. :10.000 Max. :23.000 Max. :32.00
## xa_03 xb_04 xb_05 xb_06
## Min. :-9.000 Min. :-0.3333 Min. :-3.00000 Min. :-0.3333
## 1st Qu.:-1.000 1st Qu.: 0.9056 1st Qu.:-0.66667 1st Qu.: 1.5000
## Median : 2.000 Median : 1.1039 Median : 0.00000 Median : 2.0000
## Mean : 2.199 Mean : 1.1081 Mean : 0.04583 Mean : 2.4198
## 3rd Qu.: 4.000 3rd Qu.: 1.2884 3rd Qu.: 0.75000 3rd Qu.: 3.0000
## Max. :23.000 Max. : 4.0000 Max. : 4.00000 Max. : 7.0000
## xb_07 xb_08 xn_04 xn_05
## Min. :0.000 Min. :-2.0000 Min. :-1.0000 Min. :-3.0000
## 1st Qu.:1.714 1st Qu.:-0.1000 1st Qu.: 0.3312 1st Qu.:-1.0000
## Median :2.000 Median : 0.1606 Median : 0.5655 Median :-0.5000
## Mean :2.030 Mean : 0.1593 Mean : 0.5772 Mean :-0.5039
## 3rd Qu.:2.250 3rd Qu.: 0.5000 3rd Qu.: 0.8600 3rd Qu.: 0.0000
## Max. :7.000 Max. : 4.0000 Max. : 3.0000 Max. : 3.0000
## xn_06 xn_07 xn_08 xa_04
## Min. :-1.000 Min. :-1.000 Min. :-3.0000 Min. :-2.000
## 1st Qu.: 1.000 1st Qu.: 1.067 1st Qu.:-0.7500 1st Qu.: 2.448
## Median : 1.667 Median : 1.400 Median :-0.3750 Median : 2.866
## Mean : 1.736 Mean : 1.440 Mean :-0.3311 Mean : 2.958
## 3rd Qu.: 2.500 3rd Qu.: 1.765 3rd Qu.: 0.0000 3rd Qu.: 3.302
## Max. : 6.000 Max. : 4.000 Max. : 3.0000 Max. :10.000
## xa_05 xa_06 xa_07 xa_08
## Min. :-8.0000 Min. :-2.000 Min. :-2.000 Min. :-3.0000
## 1st Qu.:-0.6667 1st Qu.: 3.500 1st Qu.: 4.000 1st Qu.: 0.6429
## Median : 0.6667 Median : 5.500 Median : 4.590 Median : 1.0667
## Mean : 0.7295 Mean : 5.934 Mean : 4.666 Mean : 1.2323
## 3rd Qu.: 2.0000 3rd Qu.: 8.000 3rd Qu.: 5.167 3rd Qu.: 1.7857
## Max. :10.0000 Max. :21.000 Max. :12.000 Max. :10.0000
## xw_01 xw_02 xw_03 xs_01
## Min. : 10.50 Min. : 0.00 Min. : 14.00 Min. :-0.09905
## 1st Qu.: 50.37 1st Qu.: 0.00 1st Qu.: 82.00 1st Qu.: 0.16001
## Median : 58.55 Median : 16.00 Median : 98.00 Median : 0.21005
## Mean : 58.31 Mean : 24.11 Mean : 87.91 Mean : 0.20989
## 3rd Qu.: 65.92 3rd Qu.: 31.00 3rd Qu.:103.00 3rd Qu.: 0.25971
## Max. :108.00 Max. :108.00 Max. :110.00 Max. : 0.67685
## xs_02 xs_03 xs_04 xs_05
## Min. :-0.73322 Min. :-0.09905 Min. :0.08563 Min. :0.00000
## 1st Qu.:-0.19427 1st Qu.: 0.30751 1st Qu.:0.25467 1st Qu.:0.06645
## Median :-0.05646 Median : 0.43543 Median :0.28865 Median :0.11691
## Mean :-0.05512 Mean : 0.50137 Mean :0.29742 Mean :0.14660
## 3rd Qu.: 0.14512 3rd Qu.: 0.66385 3rd Qu.:0.32932 3rd Qu.:0.20407
## Max. : 0.67685 Max. : 1.40500 Max. :0.74984 Max. :0.64732
## xs_06
## Min. :0.09744
## 1st Qu.:0.35745
## Median :0.51720
## Mean :0.54494
## 3rd Qu.:0.69807
## Max. :1.30883Region = YY
df %>%
filter(region == "YY") %>%
select(all_of(continuous_vars)) %>%
tibble::rowid_to_column() %>%
pivot_longer(!c("rowid")) %>%
ggplot(mapping = aes(x = value)) +
geom_histogram(bins = 50) +
facet_wrap(~name, scales = "free") +
theme_bw() +
theme(axis.text.y = element_blank())
df %>%
filter(region == "YY") %>%
select(all_of(continuous_vars)) %>%
summary()## xb_01 xb_02 xb_03 xn_01
## Min. :-2.000 Min. :-2.000 Min. :-7.00000 Min. :-3.500
## 1st Qu.: 2.557 1st Qu.: 4.000 1st Qu.:-2.00000 1st Qu.: 1.000
## Median : 3.231 Median : 7.000 Median : 0.00000 Median : 1.667
## Mean : 3.194 Mean : 6.676 Mean :-0.01351 Mean : 1.605
## 3rd Qu.: 3.980 3rd Qu.: 9.000 3rd Qu.: 1.75000 3rd Qu.: 2.231
## Max. :10.000 Max. :15.000 Max. :10.00000 Max. : 6.250
## xn_02 xn_03 xa_01 xa_02
## Min. :-3.000 Min. :-7.000 Min. :-2.000 Min. :-2.00
## 1st Qu.: 3.000 1st Qu.:-3.000 1st Qu.: 6.600 1st Qu.:10.00
## Median : 5.000 Median :-2.000 Median : 8.000 Median :16.00
## Mean : 4.662 Mean :-1.324 Mean : 7.813 Mean :15.51
## 3rd Qu.: 7.000 3rd Qu.: 1.000 3rd Qu.: 9.200 3rd Qu.:21.00
## Max. :13.000 Max. : 6.000 Max. :17.000 Max. :38.00
## xa_03 xb_04 xb_05 xb_06
## Min. :-9.000 Min. :-0.5000 Min. :-2.50000 Min. :-0.500
## 1st Qu.:-1.000 1st Qu.: 0.8622 1st Qu.:-0.66667 1st Qu.: 1.500
## Median : 1.000 Median : 1.0528 Median : 0.00000 Median : 2.000
## Mean : 1.802 Mean : 1.0448 Mean :-0.01128 Mean : 2.503
## 3rd Qu.: 5.000 3rd Qu.: 1.2881 3rd Qu.: 0.65000 3rd Qu.: 3.500
## Max. :17.000 Max. : 3.0000 Max. : 3.00000 Max. : 9.000
## xb_07 xb_08 xn_04 xn_05
## Min. :0.000 Min. :-4.00000 Min. :-2.0000 Min. :-3.0000
## 1st Qu.:1.719 1st Qu.:-0.20625 1st Qu.: 0.3864 1st Qu.:-1.0000
## Median :2.000 Median : 0.09091 Median : 0.6122 Median :-0.6667
## Mean :2.005 Mean : 0.10428 Mean : 0.6022 Mean :-0.4687
## 3rd Qu.:2.250 3rd Qu.: 0.50000 3rd Qu.: 0.8504 3rd Qu.: 0.2375
## Max. :5.000 Max. : 3.00000 Max. : 3.0000 Max. : 3.0000
## xn_06 xn_07 xn_08 xa_04
## Min. :-2.000 Min. :-2.000 Min. :-3.0000 Min. :-2.000
## 1st Qu.: 1.000 1st Qu.: 1.118 1st Qu.:-0.6667 1st Qu.: 2.337
## Median : 1.750 Median : 1.434 Median :-0.2967 Median : 2.845
## Mean : 1.958 Mean : 1.414 Mean :-0.2939 Mean : 2.740
## 3rd Qu.: 3.000 3rd Qu.: 1.667 3rd Qu.: 0.0000 3rd Qu.: 3.193
## Max. : 7.000 Max. : 3.250 Max. : 3.0000 Max. : 7.000
## xa_05 xa_06 xa_07 xa_08
## Min. :-8.0000 Min. :-2.000 Min. :-2.000 Min. :-4.0000
## 1st Qu.:-0.5000 1st Qu.: 3.375 1st Qu.: 4.000 1st Qu.: 0.3438
## Median : 0.5000 Median : 5.292 Median : 4.648 Median : 1.0000
## Mean : 0.5413 Mean : 6.210 Mean : 4.571 Mean : 0.9398
## 3rd Qu.: 2.0000 3rd Qu.: 8.000 3rd Qu.: 5.162 3rd Qu.: 1.7362
## Max. : 7.0000 Max. :23.000 Max. :11.000 Max. : 7.0000
## xw_01 xw_02 xw_03 xs_01
## Min. : 11.00 Min. : 0.00 Min. : 11.00 Min. :-0.1789
## 1st Qu.: 51.54 1st Qu.: 0.00 1st Qu.: 83.00 1st Qu.: 0.1562
## Median : 59.01 Median : 14.50 Median : 98.00 Median : 0.2070
## Mean : 58.58 Mean : 23.04 Mean : 88.18 Mean : 0.2054
## 3rd Qu.: 66.76 3rd Qu.: 35.00 3rd Qu.:103.00 3rd Qu.: 0.2521
## Max. :103.00 Max. :103.00 Max. :113.00 Max. : 0.6283
## xs_02 xs_03 xs_04 xs_05
## Min. :-0.89585 Min. :-0.1789 Min. :0.09682 Min. :0.00000
## 1st Qu.:-0.24315 1st Qu.: 0.3128 1st Qu.:0.25516 1st Qu.:0.04787
## Median :-0.07242 Median : 0.4865 Median :0.28727 Median :0.10632
## Mean :-0.07333 Mean : 0.5125 Mean :0.30026 Mean :0.14386
## 3rd Qu.: 0.07709 3rd Qu.: 0.6922 3rd Qu.:0.32621 3rd Qu.:0.19564
## Max. : 0.62832 Max. : 1.7907 Max. :0.89883 Max. :0.89883
## xs_06
## Min. :0.09682
## 1st Qu.:0.38598
## Median :0.51745
## Mean :0.53339
## 3rd Qu.:0.68155
## Max. :1.17974Region == ZZ
df %>%
filter(region == "ZZ") %>%
select(all_of(continuous_vars)) %>%
tibble::rowid_to_column() %>%
pivot_longer(!c("rowid")) %>%
ggplot(mapping = aes(x = value)) +
geom_histogram(bins = 50) +
facet_wrap(~name, scales = "free") +
theme_bw() +
theme(axis.text.y = element_blank())
df %>%
filter(region == "ZZ") %>%
select(all_of(continuous_vars)) %>%
summary()## xb_01 xb_02 xb_03 xn_01
## Min. :-4.000 Min. :-4.000 Min. :-4.000 Min. :-4.000
## 1st Qu.: 2.000 1st Qu.: 3.000 1st Qu.: 1.000 1st Qu.: 0.000
## Median : 3.208 Median : 4.500 Median : 2.000 Median : 1.333
## Mean : 3.528 Mean : 4.524 Mean : 2.602 Mean : 1.506
## 3rd Qu.: 5.000 3rd Qu.: 7.000 3rd Qu.: 4.000 3rd Qu.: 2.788
## Max. :14.000 Max. :14.000 Max. :14.000 Max. : 9.000
## xn_02 xn_03 xa_01 xa_02
## Min. :-4.000 Min. :-5.0000 Min. :-3.000 Min. :-3.00
## 1st Qu.: 1.000 1st Qu.:-1.0000 1st Qu.: 5.083 1st Qu.: 6.00
## Median : 2.000 Median : 1.0000 Median : 7.583 Median :10.00
## Mean : 2.388 Mean : 0.6701 Mean : 8.258 Mean :10.43
## 3rd Qu.: 4.000 3rd Qu.: 2.0000 3rd Qu.:11.000 3rd Qu.:14.00
## Max. : 9.000 Max. : 9.0000 Max. :35.000 Max. :35.00
## xa_03 xb_04 xb_05 xb_06
## Min. :-6.000 Min. :-2.000 Min. :-2.0000 Min. :-2.000
## 1st Qu.: 3.000 1st Qu.: 0.750 1st Qu.: 0.3333 1st Qu.: 1.000
## Median : 5.000 Median : 1.292 Median : 1.0000 Median : 1.500
## Mean : 6.269 Mean : 1.259 Mean : 0.9227 Mean : 1.636
## 3rd Qu.: 9.000 3rd Qu.: 1.665 3rd Qu.: 1.5000 3rd Qu.: 2.000
## Max. :35.000 Max. : 5.000 Max. : 5.0000 Max. : 8.000
## xb_07 xb_08 xn_04 xn_05
## Min. :-1.000 Min. :-4.0000 Min. :-4.00000 Min. :-4.0000
## 1st Qu.: 1.667 1st Qu.:-0.5000 1st Qu.: 0.02708 1st Qu.:-0.3333
## Median : 2.000 Median : 0.5000 Median : 0.55556 Median : 0.2000
## Mean : 2.204 Mean : 0.3231 Mean : 0.61960 Mean : 0.2652
## 3rd Qu.: 3.000 3rd Qu.: 1.0000 3rd Qu.: 1.00000 3rd Qu.: 1.0000
## Max. : 6.000 Max. : 5.0000 Max. : 5.00000 Max. : 5.0000
## xn_06 xn_07 xn_08 xa_04
## Min. :-4.0000 Min. :-4.000 Min. :-4.0000 Min. :-1.500
## 1st Qu.: 0.4464 1st Qu.: 1.000 1st Qu.:-1.0000 1st Qu.: 2.000
## Median : 1.0000 Median : 1.127 Median : 0.0000 Median : 3.000
## Mean : 0.9761 Mean : 1.382 Mean :-0.2118 Mean : 3.092
## 3rd Qu.: 1.5000 3rd Qu.: 2.000 3rd Qu.: 0.7292 3rd Qu.: 3.759
## Max. : 6.0000 Max. : 5.000 Max. : 5.0000 Max. :12.000
## xa_05 xa_06 xa_07 xa_08
## Min. :-3.000 Min. :-1.500 Min. :-1.000 Min. :-5.000
## 1st Qu.: 1.175 1st Qu.: 2.500 1st Qu.: 3.375 1st Qu.: 0.000
## Median : 2.250 Median : 3.667 Median : 4.536 Median : 1.667
## Mean : 2.369 Mean : 3.919 Mean : 4.814 Mean : 1.428
## 3rd Qu.: 3.237 3rd Qu.: 5.000 3rd Qu.: 6.000 3rd Qu.: 2.500
## Max. :12.000 Max. :12.000 Max. :13.000 Max. :12.000
## xw_01 xw_02 xw_03 xs_01
## Min. : 9.00 Min. : 0.00 Min. : 9.00 Min. :-0.3612
## 1st Qu.: 37.50 1st Qu.: 20.00 1st Qu.: 41.25 1st Qu.: 0.1344
## Median : 53.22 Median : 38.50 Median : 69.00 Median : 0.2393
## Mean : 55.13 Mean : 42.78 Mean : 67.35 Mean : 0.2247
## 3rd Qu.: 71.78 3rd Qu.: 62.00 3rd Qu.: 95.00 3rd Qu.: 0.3126
## Max. :104.00 Max. :104.00 Max. :110.00 Max. : 0.7548
## xs_02 xs_03 xs_04 xs_05
## Min. :-0.45588 Min. :-0.3612 Min. :0.0000 Min. :0.0000
## 1st Qu.: 0.01633 1st Qu.: 0.1679 1st Qu.:0.2268 1st Qu.:0.1516
## Median : 0.14129 Median : 0.2949 Median :0.2927 Median :0.2240
## Mean : 0.13685 Mean : 0.3150 Mean :0.3038 Mean :0.2455
## 3rd Qu.: 0.26076 3rd Qu.: 0.4330 3rd Qu.:0.3692 3rd Qu.:0.3179
## Max. : 0.69105 Max. : 1.2814 Max. :0.6896 Max. :0.6896
## xs_06
## Min. :0.0000
## 1st Qu.:0.2448
## Median :0.3538
## Mean :0.3734
## 3rd Qu.:0.4802
## Max. :1.2274In general, it appears that for most of the derived sentiment features, Region ZZ has the highest sentiment values.
Examining the correlation between the continuous inputs
df %>%
select(all_of(continuous_vars)) %>%
cor() %>%
corrplot::corrplot( type = 'upper' )
There appears to be many continuous variables that are highly correlated, both positively and negatively.
Examining the relationship between the continuous output (response) with respect to the continous inputs
df %>%
ggplot(mapping = aes(df$xb_01, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_02, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_03, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_04, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_05, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_06, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_07, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_08, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_01, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_02, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_03, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_04, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_05, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_06, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_07, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_08, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_01, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_02, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_03, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_04, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_05, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_06, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_07, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_08, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xw_01, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xw_02, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xw_03, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_01, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_02, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_03, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_04, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_05, response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_06, response)) + geom_line()
Adding Log-transformed Response
df$log_response <- log(df$response)
df %>% glimpse## Rows: 677
## Columns: 39
## $ rowid <dbl> 1, 3, 4, 5, 8, 9, 11, 14, 15, 16, 17, 18, 19, 22, 24, 25,…
## $ region <chr> "XX", "XX", "XX", "XX", "XX", "XX", "XX", "XX", "XX", "XX…
## $ customer <chr> "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B…
## $ xb_01 <dbl> 4.000000, 1.000000, 2.000000, 2.520000, 2.548387, 3.07142…
## $ xb_02 <dbl> 4, 1, 2, 11, 6, 6, 10, 12, 9, 10, 8, 10, 10, 8, 6, 10, 13…
## $ xb_03 <dbl> 4, 1, 2, -6, -1, 1, -4, -4, -2, -4, -2, -2, -2, -4, 1, -4…
## $ xn_01 <dbl> 3.0000000, 2.0000000, 2.0000000, 1.5333333, 0.8387097, 1.…
## $ xn_02 <dbl> 3, 2, 4, 9, 3, 8, 6, 10, 10, 4, 6, 8, 9, 5, 7, 12, 12, 6,…
## $ xn_03 <dbl> 3, 2, 0, -3, -4, -2, -5, -6, -3, -5, -3, -6, -4, -3, 0, -…
## $ xa_01 <dbl> 12.000000, 3.000000, 9.000000, 7.080000, 6.451613, 6.8571…
## $ xa_02 <dbl> 12, 3, 9, 29, 17, 18, 24, 27, 20, 19, 15, 24, 24, 15, 14,…
## $ xa_03 <dbl> 12, 3, 9, -7, -2, 2, -9, -5, -3, -3, -1, 1, -2, -3, 3, -4…
## $ xb_04 <dbl> 1.3333333, 1.0000000, 1.0000000, 0.8950476, 1.2247312, 1.…
## $ xb_05 <dbl> 1.3333333, 1.0000000, 1.0000000, -2.0000000, -0.5000000, …
## $ xb_06 <dbl> 1.333333, 1.000000, 1.000000, 4.000000, 4.000000, 3.00000…
## $ xb_07 <dbl> 4.000000, 1.000000, 2.000000, 1.933333, 1.967742, 1.71428…
## $ xb_08 <dbl> -1.00000000, 1.00000000, 0.00000000, -0.08000000, 0.35483…
## $ xn_04 <dbl> 1.0000000, 2.0000000, 1.0000000, 0.5268889, 0.4688172, 0.…
## $ xn_05 <dbl> 1.0000000, 2.0000000, 0.0000000, -1.0000000, -1.3333333, …
## $ xn_06 <dbl> 1.0, 2.0, 2.0, 2.5, 3.0, 2.0, 4.0, 4.0, 3.0, 2.0, 2.0, 2.…
## $ xn_07 <dbl> 3.000000, 2.000000, 2.500000, 1.493333, 1.225806, 1.64285…
## $ xn_08 <dbl> -1.0000000, 2.0000000, -1.0000000, -0.4400000, -0.4516129…
## $ xa_04 <dbl> 6.000000, 3.000000, 6.750000, 2.425333, 3.023656, 2.68571…
## $ xa_05 <dbl> 6.0000000, 3.0000000, 4.5000000, -3.5000000, -0.6666667, …
## $ xa_06 <dbl> 6.000000, 3.000000, 9.000000, 9.000000, 13.000000, 6.0000…
## $ xa_07 <dbl> 9.000000, 3.000000, 7.500000, 4.466667, 4.612903, 4.07142…
## $ xa_08 <dbl> 3.0000000, 3.0000000, 6.0000000, 0.7066667, 1.3225806, 1.…
## $ xw_01 <dbl> 23.00000, 17.00000, 52.50000, 64.52564, 54.75758, 58.3333…
## $ xw_02 <dbl> 23, 17, 48, 0, 12, 15, 0, 0, 0, 7, 14, 0, 0, 0, 8, 8, 0, …
## $ xw_03 <dbl> 23, 17, 57, 106, 105, 101, 107, 109, 109, 104, 109, 99, 1…
## $ xs_01 <dbl> 0.262073307, 0.330804757, 0.239795763, 0.142106837, 0.244…
## $ xs_02 <dbl> 0.26207331, 0.33080476, 0.19049123, -0.73321509, -0.12204…
## $ xs_03 <dbl> 0.2620733, 0.3308048, 0.2891003, 0.5500723, 1.3134719, 0.…
## $ xs_04 <dbl> 0.5375576, 0.4286607, 0.3676937, 0.2865445, 0.2375470, 0.…
## $ xs_05 <dbl> 0.5375575604, 0.4286607050, 0.2485001680, 0.0000000000, 0…
## $ xs_06 <dbl> 0.5375576, 0.4286607, 0.4868872, 0.6357541, 0.4327004, 0.…
## $ response <dbl> 2.617991, 1.184632, 2.216626, 2.726715, 1.483323, 2.03927…
## $ outcome <chr> "non_event", "non_event", "event", "non_event", "non_even…
## $ log_response <dbl> 0.9624073, 0.1694321, 0.7959862, 1.0030975, 0.3942847, 0.…df %>%
ggplot(mapping = aes(df$xb_01, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_02, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_03, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_04, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_05, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_06, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_07, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xb_08, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_01, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_02, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_03, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_04, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_05, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_06, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_07, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xn_08, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_01, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_02, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_03, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_04, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_05, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_06, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_07, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xa_08, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xw_01, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xw_02, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xw_03, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_01, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_02, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_03, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_04, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_05, log_response)) + geom_line()
df %>%
ggplot(mapping = aes(df$xs_06, log_response)) + geom_line()
Part 2: Regression - Part A
Categorical Variables Only - Linear Additive
mod_categorical <- lm(log_response ~ region + customer + outcome , data = df)Continous Variables Only - Linear Additive
mod_continous <- lm(log_response ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05
+ xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df) All Categorical + Continous inputs - Linear Additive
mod_cat_cont <- lm(log_response ~ region + customer + outcome + xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df) Interacting Categorical Input ‘Region’ with all continious inputs
mod_interact_region <- lm(log_response ~ region*xb_01 + region*xb_02 + region*xb_03 + region*xn_01 + region*xn_02 + region*xn_03 +
region*xa_01 + region*xa_02 + region*xa_03 +region*xb_04 + region*xb_05+
region*xb_06 + region*xb_07 + region*xb_08 + region*xn_04 + region*xn_05 + region*xn_06 + region*xn_07 +
region*xn_08 + region*xa_04 + region*xa_05 + region*xa_06 + region*xa_07 + region*xa_08 +
region*xw_01 + region*xw_02 + region*xw_03 + region*xs_01 + region*xs_02 + region*xs_03 + region*xs_04 +
region*xs_05 + region*xs_06, data = df)Interacting Categorical Input ‘Customer’ with all continuous inputs
mod_interact_customer <- lm(log_response ~ customer*xb_01 + customer*xb_02 + customer*xb_03 + customer*xn_01 + customer*xn_02 + customer*xn_03 +
customer*xa_01 + customer*xa_02 + customer*xa_03 +customer*xb_04 + customer*xb_05+
customer*xb_06 + customer*xb_07 + customer*xb_08 + customer*xn_04 + customer*xn_05 + customer*xn_06 + customer*xn_07 +
customer*xn_08 + customer*xa_04 + customer*xa_05 + customer*xa_06 + customer*xa_07 + customer*xa_08 +
customer*xw_01 + customer*xw_02 + customer*xw_03 + customer*xs_01 + customer*xs_02 + customer*xs_03 + customer*xs_04 +
customer*xs_05 + customer*xs_06, data = df)Examining all pairwise interactions terms of the continuous inputs
df_continuous <- df[continuous_vars]
df_continuous$log_response <- df$log_response
mod_pairwise_cont <- lm (log_response ~ (.)^2, data = df_continuous)Fitting three other basis functions
Fitting a spline model with continious xb_07 of 15 df
mod_lin_quad <- lm(log_response ~ splines::ns(xb_07, 15), data = df_continuous )The input xb_07 seemed be to statistically significant in the previous linear models.
Fitting linear model with continuous inputs and their qudratic features.
mod_quadratic <- lm(log_response ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 + xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 + I(xb_01^2) + I(xb_02^2) + I(xb_03^2) + I(xn_01^2) + I(xn_02^2) + I(xn_03^2) + I(xa_01^2) + I(xa_02^2) + I(xa_03^2) + I(xb_04^2) + I(xb_05^2) + I(xb_06^2) + I(xb_07^2) + I(xb_08^2) + I(xn_04^2) + I(xn_05^2) + I(xn_06^2) + I(xn_07^2) + I(xn_08^2) + I(xa_04^2) + I(xa_05^2) + I(xa_06^2) + I(xa_07^2) + I(xa_08^2) + I(xw_01^2) + I(xw_02^2) + I(xw_03^2) + I(xs_01^2) + I(xs_02^2) + I(xs_03^2) + I(xs_04^2) + I(xs_05^2) + I(xs_06), data = df_continuous)
mod_quadratic %>% summary()##
## Call:
## lm(formula = log_response ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 +
## xn_03 + xa_01 + xa_02 + xa_03 + xb_04 + xb_05 + xb_06 + xb_07 +
## xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 +
## xa_06 + xa_07 + xa_08 + xw_01 + xw_02 + xw_03 + xs_01 + xs_02 +
## xs_03 + xs_04 + xs_05 + xs_06 + I(xb_01^2) + I(xb_02^2) +
## I(xb_03^2) + I(xn_01^2) + I(xn_02^2) + I(xn_03^2) + I(xa_01^2) +
## I(xa_02^2) + I(xa_03^2) + I(xb_04^2) + I(xb_05^2) + I(xb_06^2) +
## I(xb_07^2) + I(xb_08^2) + I(xn_04^2) + I(xn_05^2) + I(xn_06^2) +
## I(xn_07^2) + I(xn_08^2) + I(xa_04^2) + I(xa_05^2) + I(xa_06^2) +
## I(xa_07^2) + I(xa_08^2) + I(xw_01^2) + I(xw_02^2) + I(xw_03^2) +
## I(xs_01^2) + I(xs_02^2) + I(xs_03^2) + I(xs_04^2) + I(xs_05^2) +
## I(xs_06), data = df_continuous)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.42290 -0.21820 -0.00645 0.18734 1.78412
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -5.248e-02 1.611e-01 -0.326 0.74465
## xb_01 9.331e-02 7.177e-02 1.300 0.19402
## xb_02 -3.253e-02 4.844e-02 -0.672 0.50206
## xb_03 7.670e-03 2.561e-02 0.299 0.76468
## xn_01 4.245e-02 5.900e-02 0.720 0.47209
## xn_02 2.785e-02 4.193e-02 0.664 0.50685
## xn_03 -3.795e-02 2.903e-02 -1.307 0.19158
## xa_01 -3.482e-02 3.687e-02 -0.944 0.34529
## xa_02 8.431e-03 2.331e-02 0.362 0.71773
## xa_03 1.598e-02 1.542e-02 1.036 0.30074
## xb_04 -6.303e-01 2.005e-01 -3.144 0.00175 **
## xb_05 6.367e-02 6.447e-02 0.988 0.32371
## xb_06 6.292e-02 8.704e-02 0.723 0.47002
## xb_07 1.304e-01 9.451e-02 1.380 0.16814
## xb_08 1.123e-01 5.421e-02 2.071 0.03873 *
## xn_04 8.431e-02 1.651e-01 0.511 0.60981
## xn_05 1.601e-01 6.771e-02 2.364 0.01837 *
## xn_06 2.027e-02 8.793e-02 0.231 0.81778
## xn_07 5.181e-02 8.202e-02 0.632 0.52781
## xn_08 -1.392e-01 5.465e-02 -2.547 0.01110 *
## xa_04 2.164e-02 9.885e-02 0.219 0.82675
## xa_05 8.442e-03 3.104e-02 0.272 0.78573
## xa_06 -1.946e-02 3.971e-02 -0.490 0.62431
## xa_07 8.626e-02 5.786e-02 1.491 0.13655
## xa_08 -1.300e-02 2.935e-02 -0.443 0.65807
## xw_01 2.341e-02 9.282e-03 2.522 0.01191 *
## xw_02 1.849e-03 2.907e-03 0.636 0.52506
## xw_03 -1.857e-02 7.212e-03 -2.575 0.01026 *
## xs_01 -3.936e-02 5.558e-01 -0.071 0.94357
## xs_02 -4.305e-01 2.179e-01 -1.976 0.04861 *
## xs_03 -4.488e-02 3.876e-01 -0.116 0.90788
## xs_04 -6.905e-01 7.780e-01 -0.888 0.37515
## xs_05 -7.635e-02 5.123e-01 -0.149 0.88158
## xs_06 -1.958e-01 1.802e-01 -1.086 0.27777
## I(xb_01^2) -5.065e-03 6.313e-03 -0.802 0.42263
## I(xb_02^2) 3.204e-03 2.740e-03 1.170 0.24263
## I(xb_03^2) 3.259e-03 3.650e-03 0.893 0.37234
## I(xn_01^2) 2.125e-03 6.385e-03 0.333 0.73939
## I(xn_02^2) -2.360e-03 2.846e-03 -0.829 0.40734
## I(xn_03^2) -1.643e-03 3.745e-03 -0.439 0.66108
## I(xa_01^2) 1.096e-03 1.503e-03 0.730 0.46594
## I(xa_02^2) 3.061e-04 5.552e-04 0.551 0.58157
## I(xa_03^2) -1.692e-03 1.045e-03 -1.619 0.10604
## I(xb_04^2) 1.888e-02 4.306e-02 0.439 0.66117
## I(xb_05^2) 4.055e-02 1.992e-02 2.036 0.04220 *
## I(xb_06^2) -3.457e-03 9.904e-03 -0.349 0.72717
## I(xb_07^2) 5.385e-03 1.570e-02 0.343 0.73176
## I(xb_08^2) -2.156e-02 1.856e-02 -1.162 0.24581
## I(xn_04^2) 5.545e-02 4.203e-02 1.319 0.18756
## I(xn_05^2) 6.353e-03 2.020e-02 0.315 0.75324
## I(xn_06^2) 4.552e-03 1.200e-02 0.379 0.70454
## I(xn_07^2) -2.530e-02 1.995e-02 -1.268 0.20532
## I(xn_08^2) -1.814e-02 1.798e-02 -1.009 0.31341
## I(xa_04^2) 2.523e-03 1.040e-02 0.242 0.80850
## I(xa_05^2) 1.144e-03 4.021e-03 0.284 0.77618
## I(xa_06^2) 4.625e-04 1.734e-03 0.267 0.78976
## I(xa_07^2) -5.621e-03 4.599e-03 -1.222 0.22215
## I(xa_08^2) -1.431e-03 5.264e-03 -0.272 0.78586
## I(xw_01^2) -1.079e-04 7.664e-05 -1.408 0.15968
## I(xw_02^2) -5.202e-06 3.465e-05 -0.150 0.88072
## I(xw_03^2) 1.366e-04 4.721e-05 2.893 0.00395 **
## I(xs_01^2) 4.994e-01 5.338e-01 0.936 0.34987
## I(xs_02^2) -1.512e-01 2.848e-01 -0.531 0.59568
## I(xs_03^2) -1.675e-02 2.138e-01 -0.078 0.93758
## I(xs_04^2) 2.033e+00 9.966e-01 2.040 0.04183 *
## I(xs_05^2) -5.675e-01 8.256e-01 -0.687 0.49208
## I(xs_06) NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3632 on 611 degrees of freedom
## Multiple R-squared: 0.5832, Adjusted R-squared: 0.5389
## F-statistic: 13.15 on 65 and 611 DF, p-value: < 2.2e-16Interacting linear and quadratic of three statistically significant variables from continous only linear additive model
mod_three_signif <- lm (log_response ~ (xb_04 + I(xb_04^2))*(xb_07 + I(xb_07^2)) * (xw_01 + I(xw_01^2)), data = df_continuous )Compile Performance Metrics on all 9 models
extract_metrics <- function (mod, mod_name)
{
broom::glance(mod) %>% mutate(mod_name = mod_name)
}all_metrics <- purrr::map2_dfr(list(mod_continous, mod_categorical,mod_cat_cont, mod_interact_region, mod_interact_customer,mod_pairwise_cont, mod_lin_quad, mod_quadratic, mod_three_signif), as.character(1:9), extract_metrics)
all_metrics ## # A tibble: 9 × 13
## r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.542 0.519 0.371 23.1 1.16e- 87 33 -272. 614. 772.
## 2 0.220 0.207 0.476 17.0 7.93e- 30 11 -453. 931. 990.
## 3 0.673 0.650 0.316 29.6 1.06e-124 44 -158. 408. 616.
## 4 0.727 0.679 0.303 15.2 6.28e-110 101 -96.7 399. 865.
## 5 0.821 0.679 0.303 5.79 3.41e- 55 299 46.1 510. 1870.
## 6 0.924 0.556 0.357 2.51 6.53e- 9 561 338. 451. 2994.
## 7 0.134 0.114 0.503 6.82 7.23e- 14 15 -488. 1010. 1086.
## 8 0.583 0.539 0.363 13.2 7.27e- 80 65 -240. 615. 917.
## 9 0.391 0.367 0.426 16.1 4.33e- 54 26 -368. 793. 919.
## # … with 4 more variables: deviance <dbl>, df.residual <int>, nobs <int>,
## # mod_name <chr>Using the BIC values, the third model (mod_cat_cont) is the best model.
ggplot(mapping = aes(y = all_metrics$BIC, x = all_metrics$mod_name)) + geom_point() 
Examining the Coefficients of the top three models selected using R-squared.
mod_cat_cont %>% coefplot::coefplot()
mod_cat_cont %>% summary()##
## Call:
## lm(formula = log_response ~ region + customer + outcome + xb_01 +
## xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +
## xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 +
## xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 + xw_01 +
## xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.08667 -0.19713 -0.00152 0.19722 1.55976
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.1797946 0.0995253 -1.807 0.071313 .
## regionYY 0.2761742 0.0368945 7.486 2.40e-13 ***
## regionZZ -0.2270989 0.0486347 -4.669 3.69e-06 ***
## customerB -0.1317048 0.0797339 -1.652 0.099071 .
## customerD -0.0736332 0.0866413 -0.850 0.395723
## customerE -0.1051613 0.0877251 -1.199 0.231071
## customerG -0.1092338 0.0540802 -2.020 0.043821 *
## customerK 0.2231309 0.0696342 3.204 0.001422 **
## customerM -0.1964893 0.0577596 -3.402 0.000712 ***
## customerOther -0.0531574 0.0622005 -0.855 0.393089
## customerQ -0.2331907 0.0861430 -2.707 0.006972 **
## outcomenon_event 0.0221597 0.0365570 0.606 0.544621
## xb_01 0.0083881 0.0345549 0.243 0.808280
## xb_02 0.0218866 0.0146235 1.497 0.134979
## xb_03 0.0259955 0.0219046 1.187 0.235767
## xn_01 -0.0006398 0.0328876 -0.019 0.984486
## xn_02 0.0162909 0.0152735 1.067 0.286555
## xn_03 -0.0041769 0.0186882 -0.224 0.823217
## xa_01 -0.0193491 0.0174309 -1.110 0.267402
## xa_02 0.0146935 0.0070604 2.081 0.037826 *
## xa_03 0.0001389 0.0111830 0.012 0.990094
## xb_04 -0.3471154 0.1127203 -3.079 0.002164 **
## xb_05 0.0178054 0.0528468 0.337 0.736285
## xb_06 -0.0023030 0.0278978 -0.083 0.934234
## xb_07 0.1564532 0.0435929 3.589 0.000358 ***
## xb_08 0.1109475 0.0454388 2.442 0.014892 *
## xn_04 0.2114462 0.0999907 2.115 0.034850 *
## xn_05 0.0856392 0.0430116 1.991 0.046903 *
## xn_06 0.0228028 0.0272780 0.836 0.403503
## xn_07 -0.0094721 0.0410933 -0.231 0.817776
## xn_08 -0.0957456 0.0386609 -2.477 0.013527 *
## xa_04 0.0416379 0.0549285 0.758 0.448711
## xa_05 0.0115047 0.0226307 0.508 0.611372
## xa_06 -0.0100788 0.0111927 -0.900 0.368208
## xa_07 0.0207631 0.0245260 0.847 0.397553
## xa_08 -0.0147295 0.0246192 -0.598 0.549858
## xw_01 0.0132895 0.0029451 4.512 7.64e-06 ***
## xw_02 0.0002824 0.0015227 0.185 0.852916
## xw_03 -0.0027854 0.0016893 -1.649 0.099683 .
## xs_01 -0.2029929 0.2490773 -0.815 0.415391
## xs_02 -0.1755021 0.1400204 -1.253 0.210522
## xs_03 -0.0282183 0.1132876 -0.249 0.803375
## xs_04 -0.1329774 0.3838353 -0.346 0.729124
## xs_05 0.1241057 0.2717536 0.457 0.648055
## xs_06 0.0934684 0.1510491 0.619 0.536274
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3163 on 632 degrees of freedom
## Multiple R-squared: 0.6732, Adjusted R-squared: 0.6504
## F-statistic: 29.58 on 44 and 632 DF, p-value: < 2.2e-16mod_continous %>% coefplot::coefplot()
mod_continous %>% summary()##
## Call:
## lm(formula = log_response ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 +
## xn_03 + xa_01 + xa_02 + xa_03 + xb_04 + xb_05 + xb_06 + xb_07 +
## xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 +
## xa_06 + xa_07 + xa_08 + xw_01 + xw_02 + xw_03 + xs_01 + xs_02 +
## xs_03 + xs_04 + xs_05 + xs_06, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.1981 -0.2279 -0.0121 0.2308 1.7563
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.3065731 0.0832408 -3.683 0.000250 ***
## xb_01 0.0451928 0.0399721 1.131 0.258642
## xb_02 0.0197021 0.0167751 1.174 0.240634
## xb_03 0.0067157 0.0253421 0.265 0.791094
## xn_01 0.0436725 0.0380814 1.147 0.251883
## xn_02 0.0070652 0.0176705 0.400 0.689412
## xn_03 -0.0372646 0.0215715 -1.727 0.084559 .
## xa_01 -0.0419267 0.0202378 -2.072 0.038691 *
## xa_02 0.0226529 0.0082193 2.756 0.006016 **
## xa_03 0.0040960 0.0130010 0.315 0.752823
## xb_04 -0.4689904 0.1300432 -3.606 0.000335 ***
## xb_05 0.0408992 0.0609840 0.671 0.502682
## xb_06 0.0151322 0.0324939 0.466 0.641592
## xb_07 0.1664855 0.0505356 3.294 0.001040 **
## xb_08 0.1289615 0.0527916 2.443 0.014840 *
## xn_04 0.1442231 0.1163268 1.240 0.215498
## xn_05 0.1644335 0.0497648 3.304 0.001005 **
## xn_06 0.0536260 0.0316213 1.696 0.090392 .
## xn_07 -0.0286324 0.0475703 -0.602 0.547454
## xn_08 -0.1079277 0.0451179 -2.392 0.017037 *
## xa_04 0.0200902 0.0636645 0.316 0.752436
## xa_05 0.0330188 0.0263357 1.254 0.210383
## xa_06 -0.0085964 0.0130347 -0.660 0.509809
## xa_07 0.0255978 0.0282339 0.907 0.364940
## xa_08 -0.0136748 0.0286572 -0.477 0.633393
## xw_01 0.0139666 0.0033112 4.218 2.82e-05 ***
## xw_02 -0.0007236 0.0017305 -0.418 0.675994
## xw_03 -0.0022127 0.0019083 -1.160 0.246682
## xs_01 -0.1063306 0.2914305 -0.365 0.715338
## xs_02 -0.2629219 0.1628957 -1.614 0.107007
## xs_03 -0.0161401 0.1315986 -0.123 0.902425
## xs_04 0.2308584 0.4448027 0.519 0.603930
## xs_05 -0.0926908 0.3159142 -0.293 0.769307
## xs_06 -0.0286369 0.1745249 -0.164 0.869716
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.371 on 643 degrees of freedom
## Multiple R-squared: 0.5424, Adjusted R-squared: 0.5189
## F-statistic: 23.1 on 33 and 643 DF, p-value: < 2.2e-16I am choosing the simple linear additive model to compare against the model with both the categorical and continuous predictors because I want to see if the added complexity in the categorical and continous model is actually necessary or if the continuous additive model is sufficient.
Regression - Part B
Fitting Bayesian Linear Models
Creating Design Matrix for each of the two models
Xmat_continuous <- model.matrix(~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05
+ xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df)
Xmat_cat_cont <- model.matrix( ~region + customer + outcome + xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df)Create list of information
my_info_cat_cont<- list(
yobs = df$log_response,
design_matrix = Xmat_cat_cont,
mu_beta = 0,
tau_beta = 1,
sigma_rate = 1
)
my_info_cont <- list(
yobs = df$log_response,
design_matrix = Xmat_continuous,
mu_beta = 0,
tau_beta = 1,
sigma_rate = 1
)We will be assuming a weak prior standard deviation on the regression coefficients. The prior mean will be 0.
Create Log Posterior Function
lm_logpost <- function(unknowns, my_info)
{
length_beta <- ncol(my_info$design_matrix)
beta_v <- unknowns[1:length_beta]
lik_varphi <- unknowns[length_beta + 1]
lik_sigma <- exp(lik_varphi)
X <- my_info$design_matrix
mu <- as.vector( X %*% as.matrix(beta_v) )
log_lik <- sum(dnorm(x = my_info$yobs,
mean = mu,
sd = lik_sigma,
log = TRUE))
log_prior_beta <- sum(dnorm(x = beta_v,
mean = my_info$mu_beta,
sd = my_info$tau_beta,
log = TRUE))
log_prior_sigma <- dexp(x = lik_sigma,
rate = my_info$sigma_rate,
log = TRUE)
log_prior <- log_prior_beta + log_prior_sigma
log_derive_adjust <- lik_varphi
log_lik + log_prior + log_derive_adjust
}Fitting the Bayesian Linear Models Using Laplace’s Approximation
my_laplace <- function(start_guess, logpost_func, ...)
{
# code adapted from the `LearnBayes`` function `laplace()`
fit <- optim(start_guess,
logpost_func,
gr = NULL,
...,
method = "BFGS",
hessian = TRUE,
control = list(fnscale = -1, maxit = 1001))
mode <- fit$par
post_var_matrix <- -solve(fit$hessian)
p <- length(mode)
int <- p/2 * log(2 * pi) + 0.5 * log(det(post_var_matrix)) + logpost_func(mode, ...)
# package all of the results into a list
list(mode = mode,
var_matrix = post_var_matrix,
log_evidence = int,
converge = ifelse(fit$convergence == 0,
"YES",
"NO"),
iter_counts = as.numeric(fit$counts[1]))
}laplace_cont <- my_laplace(rep(0, ncol(Xmat_continuous)+1), lm_logpost, my_info_cont)
laplace_cat_cont <- my_laplace(rep(0, ncol(Xmat_cat_cont)+1), lm_logpost, my_info_cat_cont)Using Bayes Factor to identify the better of the two models
exp(laplace_cat_cont$log_evidence) / exp(laplace_cont$log_evidence)## [1] 1.670778e+32The result of the performance metric, Bayes Factor is much greater than 1. This indicates that there is more evidence for the model with both categorical and continuous inputs than just the additive linear model with only continuous inputs.
Visualizing the regression coefficient posterior summary statistics for the best model.
viz_post_coefs <- function(post_means, post_sds, xnames)
{
tibble::tibble(
mu = post_means,
sd = post_sds,
x = xnames
) %>%
mutate(x = factor(x, levels = xnames)) %>%
ggplot(mapping = aes(x = x)) +
geom_hline(yintercept = 0, color = 'grey', linetype = 'dashed') +
geom_point(mapping = aes(y = mu)) +
geom_linerange(mapping = aes(ymin = mu - 2 * sd,
ymax = mu + 2 * sd,
group = x)) +
labs(x = 'feature', y = 'coefficient value') +
coord_flip() +
theme_bw()
}viz_post_coefs(laplace_cat_cont$mode[1:ncol(Xmat_cat_cont)],
sqrt(diag(laplace_cat_cont$var_matrix)[1:ncol(Xmat_cat_cont)]),
colnames(Xmat_cat_cont))
mod_cat_cont %>% summary()##
## Call:
## lm(formula = log_response ~ region + customer + outcome + xb_01 +
## xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +
## xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 +
## xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 + xw_01 +
## xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.08667 -0.19713 -0.00152 0.19722 1.55976
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.1797946 0.0995253 -1.807 0.071313 .
## regionYY 0.2761742 0.0368945 7.486 2.40e-13 ***
## regionZZ -0.2270989 0.0486347 -4.669 3.69e-06 ***
## customerB -0.1317048 0.0797339 -1.652 0.099071 .
## customerD -0.0736332 0.0866413 -0.850 0.395723
## customerE -0.1051613 0.0877251 -1.199 0.231071
## customerG -0.1092338 0.0540802 -2.020 0.043821 *
## customerK 0.2231309 0.0696342 3.204 0.001422 **
## customerM -0.1964893 0.0577596 -3.402 0.000712 ***
## customerOther -0.0531574 0.0622005 -0.855 0.393089
## customerQ -0.2331907 0.0861430 -2.707 0.006972 **
## outcomenon_event 0.0221597 0.0365570 0.606 0.544621
## xb_01 0.0083881 0.0345549 0.243 0.808280
## xb_02 0.0218866 0.0146235 1.497 0.134979
## xb_03 0.0259955 0.0219046 1.187 0.235767
## xn_01 -0.0006398 0.0328876 -0.019 0.984486
## xn_02 0.0162909 0.0152735 1.067 0.286555
## xn_03 -0.0041769 0.0186882 -0.224 0.823217
## xa_01 -0.0193491 0.0174309 -1.110 0.267402
## xa_02 0.0146935 0.0070604 2.081 0.037826 *
## xa_03 0.0001389 0.0111830 0.012 0.990094
## xb_04 -0.3471154 0.1127203 -3.079 0.002164 **
## xb_05 0.0178054 0.0528468 0.337 0.736285
## xb_06 -0.0023030 0.0278978 -0.083 0.934234
## xb_07 0.1564532 0.0435929 3.589 0.000358 ***
## xb_08 0.1109475 0.0454388 2.442 0.014892 *
## xn_04 0.2114462 0.0999907 2.115 0.034850 *
## xn_05 0.0856392 0.0430116 1.991 0.046903 *
## xn_06 0.0228028 0.0272780 0.836 0.403503
## xn_07 -0.0094721 0.0410933 -0.231 0.817776
## xn_08 -0.0957456 0.0386609 -2.477 0.013527 *
## xa_04 0.0416379 0.0549285 0.758 0.448711
## xa_05 0.0115047 0.0226307 0.508 0.611372
## xa_06 -0.0100788 0.0111927 -0.900 0.368208
## xa_07 0.0207631 0.0245260 0.847 0.397553
## xa_08 -0.0147295 0.0246192 -0.598 0.549858
## xw_01 0.0132895 0.0029451 4.512 7.64e-06 ***
## xw_02 0.0002824 0.0015227 0.185 0.852916
## xw_03 -0.0027854 0.0016893 -1.649 0.099683 .
## xs_01 -0.2029929 0.2490773 -0.815 0.415391
## xs_02 -0.1755021 0.1400204 -1.253 0.210522
## xs_03 -0.0282183 0.1132876 -0.249 0.803375
## xs_04 -0.1329774 0.3838353 -0.346 0.729124
## xs_05 0.1241057 0.2717536 0.457 0.648055
## xs_06 0.0934684 0.1510491 0.619 0.536274
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3163 on 632 degrees of freedom
## Multiple R-squared: 0.6732, Adjusted R-squared: 0.6504
## F-statistic: 29.58 on 44 and 632 DF, p-value: < 2.2e-16POSTERIOR UNCERTAINITY ON SIGMA
Regression - Part C
Making predictions
generate_lm_post_samples <- function(mvn_result, length_beta, num_samples)
{
MASS::mvrnorm(n = num_samples,
mu = mvn_result$mode,
Sigma = mvn_result$var_matrix) %>%
as.data.frame() %>% tibble::as_tibble() %>%
purrr::set_names(c(sprintf("beta_%02d", 0:(length_beta-1)), "varphi")) %>%
mutate(sigma = exp(varphi))
}set.seed(87123)
post_samples_cont <- generate_lm_post_samples(laplace_cont, ncol(Xmat_continuous), 2500)
post_samples_cat_cont <- generate_lm_post_samples(laplace_cat_cont, ncol(Xmat_cat_cont), 2500)post_lm_pred_samples <- function(Xnew, Bmat, sigma_vector)
{
# number of new prediction locations
M <- nrow(Xnew)
# number of posterior samples
S <- nrow(Bmat)
# matrix of linear predictors
Umat <- Xnew %*% t(Bmat)
# assmeble matrix of sigma samples
Rmat <- matrix(rep(sigma_vector, M), M, byrow = TRUE)
# generate standard normal and assemble into matrix
Zmat <- matrix(rnorm(M*S), M, byrow = TRUE)
# calculate the random observation predictions
Ymat <- Umat + Rmat * Zmat
# package together
list(Umat = Umat, Ymat = Ymat)
}make_post_lm_pred <- function(Xnew, post)
{
Bmat <- post %>% select(starts_with("beta_")) %>% as.matrix()
sigma_vector <- post %>% pull(sigma)
post_lm_pred_samples(Xnew, Bmat, sigma_vector)
}Generate Posterior predictions on the linear additive model with only continous inputs
post_pred_samples_cont <- make_post_lm_pred(Xmat_continuous,
post_samples_cont)Generate Posterior predictions on the linear additive model with categorical and continous inputs
post_pred_samples_cont <- make_post_lm_pred(Xmat_cat_cont,
post_samples_cat_cont)tidy_predict <- function(mod, xnew)
{
pred_df <- predict(mod, xnew, interval = "confidence") %>%
as.data.frame() %>% tibble::as_tibble() %>%
dplyr::select(pred = fit, ci_lwr = lwr, ci_upr = upr) %>%
bind_cols(predict(mod, xnew, interval = 'prediction') %>%
as.data.frame() %>% tibble::as_tibble() %>%
dplyr::select(pred_lwr = lwr, pred_upr = upr))
xnew %>% bind_cols(pred_df)
}pred_cont <- tidy_predict(mod_continous, df)
pred_cat_cont <- tidy_predict(mod_cat_cont, df)Visualizing Predictive Trends
pred_cat_cont %>%
ggplot(mapping = aes(x = xb_04)) +
geom_ribbon(mapping = aes(ymin = pred_lwr,
ymax = pred_upr),
fill = 'orange') +
geom_ribbon(mapping = aes(ymin = ci_lwr,
ymax = ci_upr),
fill = 'grey') +
geom_line(mapping = aes(y = pred),
color = 'black', size = 1.2) +
geom_point(data = df,
mapping = aes(x = xb_04, y = pred_cont$pred),
color = 'red', size = 2) +
facet_wrap(~region) +
theme_bw()
xw_01_vals <- pred_cont['xw_01']
min <- min(xw_01_vals)
max <- max(xw_01_vals)
mean <- (min + max) /2
med_0.25 <- (min + mean) /2
med_0.75 <- (mean + max) /2
levels <- c(min, med_0.25, mean, med_0.75, max)
levels_spaced <- rep(levels, each = nrow(df)/5)
levels_spaced[length(levels_spaced) + 1] = levels_spaced[length(levels_spaced) ]
levels_spaced[length(levels_spaced) + 1] = levels_spaced[length(levels_spaced) ]
pred_cont['levels'] = as.factor(levels_spaced)pred_cont %>%
ggplot(mapping = aes(x = xb_04)) +
geom_ribbon(mapping = aes(ymin = pred_lwr,
ymax = pred_upr,
group = pred_cont$levels),
fill = 'orange') +
geom_ribbon(mapping = aes(ymin = ci_lwr,
ymax = ci_upr,
group = pred_cont$levels),
fill = 'grey') +
geom_line(mapping = aes(y = pred_cont$pred,
group = pred_cont$levels),
color = 'black', size = 1.2) +
geom_point(data = df,
mapping = aes(x = xb_04, y = pred_cont$pred),
color = 'red', size = 2) + facet_wrap(~pred_cont$levels) +
theme_bw()
In the second plot, the plot is faceted with the variable xw_01. The predictions look pretty consistent. They majority of the data points are between 0 and 2.
Regresiion - Part D
Training Linear Models
df_reg <- df %>%
select(region, customer, starts_with('x'), log_response)my_metric <- "RMSE"
my_ctrl <- trainControl(method = "repeatedcv" , number = 5, repeats = 5, my_metric)All categorical and continuous inputs (also model selected from Part A)
cat_cont_tune <- caret::train(log_response ~ ., data = df_reg, method = 'lm' , metric = my_metric,
preProcess = c('center','scale'), trControl = my_ctrl)All pairwise interactions of continuous inputs and additive categorical features
pairwise_tune <- caret::train(log_response ~ (.)^2 + region + customer ,data = df_reg, method = 'lm', metric = my_metric,
preProcess = c('center','scale'), trControl = my_ctrl)## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQTraining the second model from Regression Part A (mod_continuous)
continuous_tune <- caret::train(log_response ~ . ,data = df_continuous, method = 'lm', metric = my_metric,
preProcess = c('center','scale'), trControl = my_ctrl)
continuous_tune## Linear Regression
##
## 677 samples
## 33 predictor
##
## Pre-processing: centered (33), scaled (33)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 543, 542, 541, 541, 541, 542, ...
## Resampling results:
##
## RMSE Rsquared MAE
## 0.3827837 0.4958512 0.2958764
##
## Tuning parameter 'intercept' was held constant at a value of TRUERegularized Regression with Elastic Net - Using glmnet
All pairwise interactions of continuous inputs including additive categorical features
pairwise_enet <- caret::train(log_response ~ (.)^2 + region + customer ,data = df_reg, method = 'glmnet', metric = my_metric,
preProcess = c('center','scale'), trControl = my_ctrl)## Warning in preProcess.default(method = c("center", "scale"), x =
## structure(c(0, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQRegularized Regression with Elastic Net - mod_cat_cont
mod_cat_cont_enet <- caret::train(log_response ~ .,data = df_reg, method = 'glmnet', metric = my_metric,
preProcess = c('center','scale'), trControl = my_ctrl)Using Neural Network to Train, Tune and Evaluate the mod_cat_cont model
my_metric <- "RMSE"
my_ctrl <- trainControl(method = "repeatedcv" , number = 5, repeats = 5, my_metric)set.seed(4321)
fit_nnet<- train(log_response ~ .,
data = df_reg, method = "nnet", metric = my_metric, trControl = my_ctrl,
preProcess = c('center', 'scale'),
trace = FALSE)## Warning in nominalTrainWorkflow(x = x, y = y, wts = weights, info = trainInfo, :
## There were missing values in resampled performance measures.Using Random Forest to Train, evaluate, and tune the mod_cat_cont model.
set.seed(4321)
fit_rf <- train(log_response ~ .,
data = df_reg, method = "rf", metric = my_metric, trControl = my_ctrl,
trace = FALSE)Using Extrem Gradient Boosted Tree to Train, evaluate, and tune the mod_cat_cont model.
set.seed(4321)
fit_xgb <- train(log_response ~. ,
data = df_reg, method = 'xgbTree', metric = my_metric, trControl = my_ctrl, preProcess = c('center', 'scale'), verbosity = 0)Using Partial Least Squares to Train, evaluate, and tune the mod_cat_cont model.
set.seed(4321)
fit_pls <- train(log_response ~ .,
data = df_reg, method = "pls", metric = my_metric, trControl = my_ctrl,
preProcess = c('center', 'scale'), importance = TRUE,
trace = FALSE)Using KNN to Train, evaluate, and tune the mod_cat_cont model.
fit_knn <- train(log_response ~ .,
data = df_reg, method = "knn", metric = my_metric, trControl = my_ctrl,
preProcess = c('center', 'scale'))Using the preprocessing options of centering and scaling, using RMSE for the performance metric, and 5 fold CV repeated 5 times, the best model
cat_cont_tune## Linear Regression
##
## 677 samples
## 35 predictor
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 543, 542, 541, 541, 541, ...
## Resampling results:
##
## RMSE Rsquared MAE
## 0.3316742 0.6191067 0.2571752
##
## Tuning parameter 'intercept' was held constant at a value of TRUEpairwise_tune## Linear Regression
##
## 677 samples
## 35 predictor
##
## Pre-processing: centered (917), scaled (917)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 543, 542, 541, 541, 541, 541, ...
## Resampling results:
##
## RMSE Rsquared MAE
## 4.384736e+13 0.007700463 5.934113e+12
##
## Tuning parameter 'intercept' was held constant at a value of TRUEpairwise_enet## glmnet
##
## 677 samples
## 35 predictor
##
## Pre-processing: centered (917), scaled (917)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 542, 541, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## alpha lambda RMSE Rsquared MAE
## 0.10 0.01986111 0.2895734 0.7115773 0.2209406
## 0.10 0.06280634 0.2892408 0.7104730 0.2224893
## 0.10 0.19861107 0.3057961 0.6821587 0.2377119
## 0.55 0.01986111 0.2930417 0.7025400 0.2256930
## 0.55 0.06280634 0.3165188 0.6630571 0.2456847
## 0.55 0.19861107 0.3851537 0.5762559 0.3009650
## 1.00 0.01986111 0.3028425 0.6840027 0.2343825
## 1.00 0.06280634 0.3398100 0.6286261 0.2629006
## 1.00 0.19861107 0.4496350 0.5268355 0.3593552
##
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were alpha = 0.1 and lambda = 0.06280634.fit_nnet## Neural Network
##
## 677 samples
## 35 predictor
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 544, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## size decay RMSE Rsquared MAE
## 1 0e+00 0.5527321 0.5116873 0.4470228
## 1 1e-04 0.4491423 0.3967188 0.3495732
## 1 1e-01 0.3981355 0.5065941 0.3007541
## 3 0e+00 0.5329273 0.4171356 0.4269987
## 3 1e-04 0.4296851 0.4239912 0.3305346
## 3 1e-01 0.3894848 0.5367057 0.2901814
## 5 0e+00 0.5115434 0.4140724 0.4083407
## 5 1e-04 0.4153886 0.4471864 0.3167712
## 5 1e-01 0.3867758 0.5465026 0.2885699
##
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were size = 5 and decay = 0.1.fit_rf## Random Forest
##
## 677 samples
## 35 predictor
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 544, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## mtry RMSE Rsquared MAE
## 2 0.3558164 0.6208213 0.2753076
## 22 0.3169718 0.6593186 0.2415222
## 43 0.3194658 0.6478606 0.2439380
##
## RMSE was used to select the optimal model using the smallest value.
## The final value used for the model was mtry = 22.fit_xgb## eXtreme Gradient Boosting
##
## 677 samples
## 35 predictor
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 544, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## eta max_depth colsample_bytree subsample nrounds RMSE Rsquared
## 0.3 1 0.6 0.50 50 0.3419299 0.5921881
## 0.3 1 0.6 0.50 100 0.3404880 0.5980447
## 0.3 1 0.6 0.50 150 0.3404908 0.5997819
## 0.3 1 0.6 0.75 50 0.3388544 0.6006702
## 0.3 1 0.6 0.75 100 0.3348654 0.6092459
## 0.3 1 0.6 0.75 150 0.3361678 0.6069911
## 0.3 1 0.6 1.00 50 0.3403684 0.5998813
## 0.3 1 0.6 1.00 100 0.3332592 0.6134024
## 0.3 1 0.6 1.00 150 0.3320072 0.6162209
## 0.3 1 0.8 0.50 50 0.3394429 0.5970773
## 0.3 1 0.8 0.50 100 0.3373015 0.6039766
## 0.3 1 0.8 0.50 150 0.3376955 0.6052552
## 0.3 1 0.8 0.75 50 0.3388239 0.6005342
## 0.3 1 0.8 0.75 100 0.3354910 0.6080990
## 0.3 1 0.8 0.75 150 0.3367270 0.6058532
## 0.3 1 0.8 1.00 50 0.3387704 0.6040822
## 0.3 1 0.8 1.00 100 0.3325038 0.6150634
## 0.3 1 0.8 1.00 150 0.3320288 0.6159957
## 0.3 2 0.6 0.50 50 0.3262382 0.6301831
## 0.3 2 0.6 0.50 100 0.3259037 0.6331146
## 0.3 2 0.6 0.50 150 0.3280969 0.6302533
## 0.3 2 0.6 0.75 50 0.3145717 0.6544190
## 0.3 2 0.6 0.75 100 0.3144640 0.6567671
## 0.3 2 0.6 0.75 150 0.3185565 0.6497880
## 0.3 2 0.6 1.00 50 0.3126478 0.6592319
## 0.3 2 0.6 1.00 100 0.3108312 0.6632143
## 0.3 2 0.6 1.00 150 0.3129642 0.6590925
## 0.3 2 0.8 0.50 50 0.3242988 0.6347042
## 0.3 2 0.8 0.50 100 0.3288370 0.6282793
## 0.3 2 0.8 0.50 150 0.3349609 0.6171941
## 0.3 2 0.8 0.75 50 0.3155080 0.6537373
## 0.3 2 0.8 0.75 100 0.3156270 0.6551699
## 0.3 2 0.8 0.75 150 0.3184164 0.6495158
## 0.3 2 0.8 1.00 50 0.3128396 0.6595172
## 0.3 2 0.8 1.00 100 0.3114758 0.6626752
## 0.3 2 0.8 1.00 150 0.3141036 0.6578625
## 0.3 3 0.6 0.50 50 0.3273894 0.6297015
## 0.3 3 0.6 0.50 100 0.3323138 0.6224203
## 0.3 3 0.6 0.50 150 0.3352044 0.6173099
## 0.3 3 0.6 0.75 50 0.3156065 0.6533186
## 0.3 3 0.6 0.75 100 0.3181004 0.6493618
## 0.3 3 0.6 0.75 150 0.3196355 0.6469989
## 0.3 3 0.6 1.00 50 0.3106563 0.6646802
## 0.3 3 0.6 1.00 100 0.3117320 0.6626549
## 0.3 3 0.6 1.00 150 0.3132199 0.6598145
## 0.3 3 0.8 0.50 50 0.3268448 0.6321885
## 0.3 3 0.8 0.50 100 0.3330008 0.6227453
## 0.3 3 0.8 0.50 150 0.3370168 0.6146264
## 0.3 3 0.8 0.75 50 0.3161041 0.6523706
## 0.3 3 0.8 0.75 100 0.3189362 0.6480517
## 0.3 3 0.8 0.75 150 0.3217450 0.6426814
## 0.3 3 0.8 1.00 50 0.3152196 0.6532242
## 0.3 3 0.8 1.00 100 0.3177724 0.6491622
## 0.3 3 0.8 1.00 150 0.3197928 0.6454561
## 0.4 1 0.6 0.50 50 0.3466394 0.5822971
## 0.4 1 0.6 0.50 100 0.3465491 0.5862537
## 0.4 1 0.6 0.50 150 0.3510794 0.5792733
## 0.4 1 0.6 0.75 50 0.3392946 0.5982466
## 0.4 1 0.6 0.75 100 0.3358930 0.6073641
## 0.4 1 0.6 0.75 150 0.3383143 0.6039517
## 0.4 1 0.6 1.00 50 0.3419257 0.5928643
## 0.4 1 0.6 1.00 100 0.3379763 0.6026294
## 0.4 1 0.6 1.00 150 0.3376006 0.6038548
## 0.4 1 0.8 0.50 50 0.3424399 0.5929237
## 0.4 1 0.8 0.50 100 0.3440242 0.5923853
## 0.4 1 0.8 0.50 150 0.3519267 0.5787778
## 0.4 1 0.8 0.75 50 0.3387846 0.5995815
## 0.4 1 0.8 0.75 100 0.3384034 0.6033303
## 0.4 1 0.8 0.75 150 0.3413484 0.5976856
## 0.4 1 0.8 1.00 50 0.3392098 0.5989187
## 0.4 1 0.8 1.00 100 0.3350487 0.6088006
## 0.4 1 0.8 1.00 150 0.3349958 0.6097014
## 0.4 2 0.6 0.50 50 0.3402169 0.6033320
## 0.4 2 0.6 0.50 100 0.3452006 0.5970327
## 0.4 2 0.6 0.50 150 0.3525542 0.5853051
## 0.4 2 0.6 0.75 50 0.3294095 0.6252427
## 0.4 2 0.6 0.75 100 0.3343112 0.6180474
## 0.4 2 0.6 0.75 150 0.3366650 0.6145304
## 0.4 2 0.6 1.00 50 0.3229860 0.6360581
## 0.4 2 0.6 1.00 100 0.3224750 0.6384832
## 0.4 2 0.6 1.00 150 0.3252853 0.6332374
## 0.4 2 0.8 0.50 50 0.3327715 0.6205480
## 0.4 2 0.8 0.50 100 0.3405982 0.6085293
## 0.4 2 0.8 0.50 150 0.3460331 0.6002101
## 0.4 2 0.8 0.75 50 0.3270486 0.6310318
## 0.4 2 0.8 0.75 100 0.3300480 0.6273127
## 0.4 2 0.8 0.75 150 0.3329577 0.6228018
## 0.4 2 0.8 1.00 50 0.3227387 0.6377379
## 0.4 2 0.8 1.00 100 0.3251971 0.6340727
## 0.4 2 0.8 1.00 150 0.3275663 0.6299797
## 0.4 3 0.6 0.50 50 0.3458639 0.5949823
## 0.4 3 0.6 0.50 100 0.3562958 0.5790781
## 0.4 3 0.6 0.50 150 0.3574546 0.5788341
## 0.4 3 0.6 0.75 50 0.3289164 0.6291671
## 0.4 3 0.6 0.75 100 0.3350389 0.6175949
## 0.4 3 0.6 0.75 150 0.3373865 0.6132860
## 0.4 3 0.6 1.00 50 0.3226524 0.6395880
## 0.4 3 0.6 1.00 100 0.3251702 0.6357800
## 0.4 3 0.6 1.00 150 0.3267640 0.6326968
## 0.4 3 0.8 0.50 50 0.3530398 0.5808084
## 0.4 3 0.8 0.50 100 0.3588508 0.5720844
## 0.4 3 0.8 0.50 150 0.3598958 0.5713289
## 0.4 3 0.8 0.75 50 0.3299060 0.6280591
## 0.4 3 0.8 0.75 100 0.3359804 0.6179190
## 0.4 3 0.8 0.75 150 0.3376207 0.6155715
## 0.4 3 0.8 1.00 50 0.3221263 0.6399295
## 0.4 3 0.8 1.00 100 0.3253440 0.6338670
## 0.4 3 0.8 1.00 150 0.3262925 0.6324997
## MAE
## 0.2633640
## 0.2603171
## 0.2603845
## 0.2610766
## 0.2590276
## 0.2596427
## 0.2636127
## 0.2584312
## 0.2571132
## 0.2624094
## 0.2616045
## 0.2615168
## 0.2610343
## 0.2591480
## 0.2594892
## 0.2618004
## 0.2575032
## 0.2568376
## 0.2529613
## 0.2527136
## 0.2552934
## 0.2403881
## 0.2412629
## 0.2442970
## 0.2426018
## 0.2406064
## 0.2417833
## 0.2506950
## 0.2537268
## 0.2594871
## 0.2436880
## 0.2440602
## 0.2461886
## 0.2415202
## 0.2409330
## 0.2423271
## 0.2542300
## 0.2580360
## 0.2600106
## 0.2442238
## 0.2466920
## 0.2475668
## 0.2396174
## 0.2409338
## 0.2420953
## 0.2519150
## 0.2568105
## 0.2608309
## 0.2453160
## 0.2479695
## 0.2502069
## 0.2432317
## 0.2450319
## 0.2468421
## 0.2672052
## 0.2678211
## 0.2701550
## 0.2629090
## 0.2597291
## 0.2611474
## 0.2638241
## 0.2606790
## 0.2601122
## 0.2636715
## 0.2631573
## 0.2696653
## 0.2625938
## 0.2612785
## 0.2625051
## 0.2618128
## 0.2584927
## 0.2583001
## 0.2626486
## 0.2663857
## 0.2731184
## 0.2545529
## 0.2593342
## 0.2620724
## 0.2482634
## 0.2478844
## 0.2497067
## 0.2582444
## 0.2642135
## 0.2687524
## 0.2518088
## 0.2543809
## 0.2565896
## 0.2486644
## 0.2509991
## 0.2526135
## 0.2687348
## 0.2774802
## 0.2800297
## 0.2554903
## 0.2605910
## 0.2620428
## 0.2483815
## 0.2507025
## 0.2521484
## 0.2739793
## 0.2800020
## 0.2812212
## 0.2540091
## 0.2579277
## 0.2593607
## 0.2497591
## 0.2531979
## 0.2539270
##
## Tuning parameter 'gamma' was held constant at a value of 0
## Tuning
## parameter 'min_child_weight' was held constant at a value of 1
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were nrounds = 50, max_depth = 3, eta
## = 0.3, gamma = 0, colsample_bytree = 0.6, min_child_weight = 1 and subsample
## = 1.fit_pls## Partial Least Squares
##
## 677 samples
## 35 predictor
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 544, 541, 541, 541, 541, ...
## Resampling results across tuning parameters:
##
## ncomp RMSE Rsquared MAE
## 1 0.4050463 0.4304784 0.3127297
## 2 0.3440625 0.5885271 0.2631066
## 3 0.3392788 0.6003989 0.2611801
##
## RMSE was used to select the optimal model using the smallest value.
## The final value used for the model was ncomp = 3.fit_knn## k-Nearest Neighbors
##
## 677 samples
## 35 predictor
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 541, 543, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## k RMSE Rsquared MAE
## 5 0.3614280 0.5483458 0.2843570
## 7 0.3571253 0.5656164 0.2822834
## 9 0.3567971 0.5738453 0.2825517
##
## RMSE was used to select the optimal model using the smallest value.
## The final value used for the model was k = 9.When trained, tuned, and evaluated the best model is The pairwise interactions tuned through elastic net.
Part 3 - Classification Part A
Creating binary outcome column based on outcome column
df['numeric_outcome'] <- ifelse(df$outcome == 'event', 1, 0)
df_class <- df %>%
mutate(outcome = factor(outcome, levels = c("event", "non_event"))) %>%
mutate(numeric_outcome = factor(numeric_outcome, levels = c(1,0)))glm_categorical <- glm(outcome ~ region + customer + outcome , data = df_class, family = "binomial")## Warning in model.matrix.default(mt, mf, contrasts): the response appeared on the
## right-hand side and was dropped## Warning in model.matrix.default(mt, mf, contrasts): problem with term 3 in
## model.matrix: no columns are assignedWith a model just containing the categorical variables of customer and region, the variables that are statistically significant are regionZZ, customerB, customerD, customerE, customerOther.
Continous Variables Only - Linear Additive
glm_continous <- glm(outcome ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05
+ xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df_class, family = "binomial") Most of the continuous inputs are not statistically significant to the binary outcome. The inputs that are considered to be significant are xn_03, xa_01, xb_07, xn_04, xn_05,xn_07, xn_08, xa_05, xw_03 .The intercept of the model is also significant.
All Categorical + Continous inputs - Linear Additive
glm_cat_cont <- glm(outcome ~ region + customer + outcome + xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df_class, family = "binomial") ## Warning in model.matrix.default(mt, mf, contrasts): the response appeared on the
## right-hand side and was dropped## Warning in model.matrix.default(mt, mf, contrasts): problem with term 3 in
## model.matrix: no columns are assignedInteracting Categorical Input ‘Region’ with all continious inputs
glm_interact_region <- glm(outcome ~ region*xb_01 + region*xb_02 + region*xb_03 + region*xn_01 + region*xn_02 + region*xn_03 +
region*xa_01 + region*xa_02 + region*xa_03 +region*xb_04 + region*xb_05+
region*xb_06 + region*xb_07 + region*xb_08 + region*xn_04 + region*xn_05 + region*xn_06 + region*xn_07 +
region*xn_08 + region*xa_04 + region*xa_05 + region*xa_06 + region*xa_07 + region*xa_08 +
region*xw_01 + region*xw_02 + region*xw_03 + region*xs_01 + region*xs_02 + region*xs_03 + region*xs_04 +
region*xs_05 + region*xs_06, data = df_class, family = "binomial")Interacting Categorical Input ‘Customer’ with all continuous inputs
glm_interact_customer <- glm(outcome ~ customer*xb_01 + customer*xb_02 + customer*xb_03 + customer*xn_01 + customer*xn_02 + customer*xn_03 +
customer*xa_01 + customer*xa_02 + customer*xa_03 +customer*xb_04 + customer*xb_05+
customer*xb_06 + customer*xb_07 + customer*xb_08 + customer*xn_04 + customer*xn_05 + customer*xn_06 + customer*xn_07 +
customer*xn_08 + customer*xa_04 + customer*xa_05 + customer*xa_06 + customer*xa_07 + customer*xa_08 +
customer*xw_01 + customer*xw_02 + customer*xw_03 + customer*xs_01 + customer*xs_02 + customer*xs_03 + customer*xs_04 +
customer*xs_05 + customer*xs_06, data = df_class, family = "binomial")## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredExamining all pairwise interactions terms of the continuous inputs
df_continuous <- df_continuous[-length(df_continuous)]
df_continuous['numeric_outcome'] <- df$numeric_outcome
df_continuous['log_response'] <- df$log_responseglm_pairwise_cont <- glm (numeric_outcome ~ (.)^2, data = df_continuous, family = "binomial")## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredFitting three other basis functions
Fitting a spline model with continious xb_03 of 15 df
df_continuous['outcome'] <- df_class$outcome
glm_spline <- glm(outcome ~ splines::ns(xw_03, 15), data = df_continuous, family = "binomial" )The input xb_07 seemed be to statistically significant in the previous linear models.
Fitting linear model with continuous inputs and their qudratic features.
glm_quadratic <- glm(outcome ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 + xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06 + I(xb_01^2) + I(xb_02^2) + I(xb_03^2) + I(xn_01^2) + I(xn_02^2) + I(xn_03^2) + I(xa_01^2) + I(xa_02^2) + I(xa_03^2) + I(xb_04^2) + I(xb_05^2) + I(xb_06^2) + I(xb_07^2) + I(xb_08^2) + I(xn_04^2) + I(xn_05^2) + I(xn_06^2) + I(xn_07^2) + I(xn_08^2) + I(xa_04^2) + I(xa_05^2) + I(xa_06^2) + I(xa_07^2) + I(xa_08^2) + I(xw_01^2) + I(xw_02^2) + I(xw_03^2) + I(xs_01^2) + I(xs_02^2) + I(xs_03^2) + I(xs_04^2) + I(xs_05^2) + I(xs_06), data = df_continuous, family = 'binomial') ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredInteracting linear and quadratic of three statistically significant variables from continous only linear additive model
glm_three_signif <- glm (outcome ~ (xw_03 + I(xw_03^2))*(xn_07 + I(xn_07^2)) * (xn_08+ I(xn_08^2)), data = df_continuous, family = "binomial" )## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredThese models are mostly consistent with the regression portion, with some varying differences in variable significance. THere were some warning messages that fitted probabilities were numerically 0 or 1 occurred.
Extracting Metrics from the 9 GLM models to determine the best models.
extract_metrics <- function (mod, mod_name)
{
broom::glance(mod) %>% mutate(mod_name = mod_name)
}all_metrics <- purrr::map2_dfr(list(glm_continous, glm_categorical, glm_cat_cont, glm_interact_region, glm_interact_customer,glm_pairwise_cont, glm_spline, glm_quadratic, glm_three_signif), as.character(1:9), extract_metrics)
all_metrics ## # A tibble: 9 × 9
## null.deviance df.null logLik AIC BIC deviance df.residual nobs mod_name
## <dbl> <int> <dbl> <dbl> <dbl> <dbl> <int> <int> <chr>
## 1 654. 676 -2.14e+2 496. 650. 4.28e+2 643 677 1
## 2 654. 676 -3.11e+2 644. 693. 6.22e+2 666 677 2
## 3 654. 676 -2.00e+2 489. 688. 4.01e+2 633 677 3
## 4 654. 676 -1.86e+2 575. 1036. 3.71e+2 575 677 4
## 5 654. 676 -2.13e+3 4853. 6208. 4.25e+3 377 677 5
## 6 654. 676 -2.96e-9 1192. 3885. 5.92e-9 81 677 6
## 7 654. 676 -3.22e+2 675. 748. 6.43e+2 661 677 7
## 8 654. 676 -1.95e+2 522. 821. 3.90e+2 611 677 8
## 9 654. 676 -2.40e+2 534. 656. 4.80e+2 650 677 9Using BIC again, the best model is model 1 – model with all continuous inputs. The top three models are model 1, 9, 3 (glm_continuous, glm_three_signif, glm_cat_cont)
ggplot(mapping = aes(y = all_metrics$BIC, x = all_metrics$mod_name)) + geom_point() 
Visualizing the coefficient summaries of the top three models.
glm_continous %>% coefplot::coefplot()
glm_continous %>% summary()##
## Call:
## glm(formula = outcome ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 +
## xn_03 + xa_01 + xa_02 + xa_03 + xb_04 + xb_05 + xb_06 + xb_07 +
## xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 +
## xa_06 + xa_07 + xa_08 + xw_01 + xw_02 + xw_03 + xs_01 + xs_02 +
## xs_03 + xs_04 + xs_05 + xs_06, family = "binomial", data = df_class)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.53568 0.04411 0.25432 0.54178 2.29122
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.74664 0.83452 2.093 0.03635 *
## xb_01 -0.23535 0.33484 -0.703 0.48213
## xb_02 0.06593 0.12905 0.511 0.60943
## xb_03 0.02335 0.20140 0.116 0.90770
## xn_01 0.25124 0.39183 0.641 0.52140
## xn_02 0.21489 0.15341 1.401 0.16130
## xn_03 0.37185 0.16961 2.192 0.02835 *
## xa_01 0.30987 0.17743 1.746 0.08074 .
## xa_02 -0.04805 0.06648 -0.723 0.46984
## xa_03 -0.02498 0.11263 -0.222 0.82445
## xb_04 -0.46985 1.21480 -0.387 0.69892
## xb_05 -0.48612 0.48901 -0.994 0.32018
## xb_06 0.34854 0.27853 1.251 0.21080
## xb_07 0.87367 0.51166 1.708 0.08773 .
## xb_08 0.15574 0.52919 0.294 0.76853
## xn_04 -2.15908 1.28253 -1.683 0.09229 .
## xn_05 0.72395 0.39263 1.844 0.06521 .
## xn_06 0.38584 0.28749 1.342 0.17955
## xn_07 1.02626 0.48923 2.098 0.03593 *
## xn_08 0.90325 0.45462 1.987 0.04694 *
## xa_04 -0.92562 0.64324 -1.439 0.15015
## xa_05 0.42427 0.21961 1.932 0.05337 .
## xa_06 0.02034 0.11627 0.175 0.86114
## xa_07 -0.18466 0.29681 -0.622 0.53385
## xa_08 0.30580 0.29036 1.053 0.29227
## xw_01 0.03307 0.02655 1.245 0.21304
## xw_02 0.01233 0.01456 0.847 0.39725
## xw_03 -0.04307 0.01537 -2.802 0.00509 **
## xs_01 0.45776 2.53394 0.181 0.85664
## xs_02 -1.92673 1.38234 -1.394 0.16337
## xs_03 1.69319 1.12978 1.499 0.13395
## xs_04 -2.38492 3.72792 -0.640 0.52234
## xs_05 0.08946 2.69624 0.033 0.97353
## xs_06 -0.34687 1.37884 -0.252 0.80138
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 653.59 on 676 degrees of freedom
## Residual deviance: 428.46 on 643 degrees of freedom
## AIC: 496.46
##
## Number of Fisher Scoring iterations: 7glm_three_signif %>% coefplot::coefplot()
glm_three_signif %>% summary()##
## Call:
## glm(formula = outcome ~ (xw_03 + I(xw_03^2)) * (xn_07 + I(xn_07^2)) *
## (xn_08 + I(xn_08^2)), family = "binomial", data = df_continuous)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.45078 0.00251 0.31577 0.64926 1.85648
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.5079899 2.4239212 0.622 0.53386
## xw_03 -0.1133387 0.1183186 -0.958 0.33811
## I(xw_03^2) 0.0016811 0.0012002 1.401 0.16132
## xn_07 -8.9612680 6.2522200 -1.433 0.15177
## I(xn_07^2) 8.9613940 4.2538033 2.107 0.03515 *
## xn_08 8.9198798 6.6238457 1.347 0.17810
## I(xn_08^2) 4.6541940 3.8476501 1.210 0.22642
## xw_03:xn_07 0.4596920 0.2346506 1.959 0.05011 .
## xw_03:I(xn_07^2) -0.3155133 0.1321130 -2.388 0.01693 *
## I(xw_03^2):xn_07 -0.0048550 0.0021298 -2.280 0.02263 *
## I(xw_03^2):I(xn_07^2) 0.0028131 0.0010516 2.675 0.00747 **
## xw_03:xn_08 -0.3436373 0.2511866 -1.368 0.17129
## xw_03:I(xn_08^2) -0.1533256 0.1394335 -1.100 0.27149
## I(xw_03^2):xn_08 0.0034004 0.0021444 1.586 0.11280
## I(xw_03^2):I(xn_08^2) 0.0012730 0.0010982 1.159 0.24638
## xn_07:xn_08 -5.5922877 9.2228273 -0.606 0.54428
## xn_07:I(xn_08^2) 1.9416192 5.6414443 0.344 0.73072
## I(xn_07^2):xn_08 3.5760309 3.0865240 1.159 0.24662
## I(xn_07^2):I(xn_08^2) -1.6844852 1.8139305 -0.929 0.35308
## xw_03:xn_07:xn_08 0.3202394 0.3727563 0.859 0.39028
## xw_03:xn_07:I(xn_08^2) -0.0303842 0.2138368 -0.142 0.88701
## xw_03:I(xn_07^2):xn_08 -0.1523356 0.1376059 -1.107 0.26828
## xw_03:I(xn_07^2):I(xn_08^2) 0.0388796 0.0745086 0.522 0.60180
## I(xw_03^2):xn_07:xn_08 -0.0039410 0.0032972 -1.195 0.23198
## I(xw_03^2):xn_07:I(xn_08^2) -0.0002030 0.0017093 -0.119 0.90549
## I(xw_03^2):I(xn_07^2):xn_08 0.0017026 0.0012913 1.319 0.18731
## I(xw_03^2):I(xn_07^2):I(xn_08^2) -0.0000926 0.0006208 -0.149 0.88142
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 653.59 on 676 degrees of freedom
## Residual deviance: 479.88 on 650 degrees of freedom
## AIC: 533.88
##
## Number of Fisher Scoring iterations: 13glm_cat_cont %>% coefplot::coefplot()
glm_cat_cont %>% summary()##
## Call:
## glm(formula = outcome ~ region + customer + outcome + xb_01 +
## xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +
## xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 +
## xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 + xw_01 +
## xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06,
## family = "binomial", data = df_class)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.72956 0.02986 0.19193 0.48775 2.51713
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.079176 1.040892 -0.076 0.93937
## regionYY 0.459934 0.382696 1.202 0.22943
## regionZZ 1.585516 0.493926 3.210 0.00133 **
## customerB 2.420042 0.858364 2.819 0.00481 **
## customerD 3.626300 1.118994 3.241 0.00119 **
## customerE 4.070174 1.305794 3.117 0.00183 **
## customerG 0.799423 0.597087 1.339 0.18061
## customerK 1.340608 0.751047 1.785 0.07426 .
## customerM 0.172952 0.635200 0.272 0.78541
## customerOther 1.533744 0.659114 2.327 0.01997 *
## customerQ 1.958051 0.915096 2.140 0.03238 *
## xb_01 -0.191744 0.353659 -0.542 0.58770
## xb_02 -0.018087 0.134240 -0.135 0.89282
## xb_03 0.042694 0.211803 0.202 0.84025
## xn_01 0.341512 0.399361 0.855 0.39247
## xn_02 0.188469 0.154751 1.218 0.22327
## xn_03 0.399131 0.177306 2.251 0.02438 *
## xa_01 0.364592 0.190021 1.919 0.05502 .
## xa_02 -0.028789 0.071942 -0.400 0.68903
## xa_03 -0.033717 0.117716 -0.286 0.77455
## xb_04 -0.098036 1.291060 -0.076 0.93947
## xb_05 -0.652151 0.513553 -1.270 0.20413
## xb_06 0.302941 0.298214 1.016 0.30970
## xb_07 0.825085 0.528613 1.561 0.11856
## xb_08 0.073412 0.550694 0.133 0.89395
## xn_04 -2.432393 1.318686 -1.845 0.06510 .
## xn_05 0.633605 0.415522 1.525 0.12730
## xn_06 0.271087 0.301647 0.899 0.36882
## xn_07 1.278058 0.508250 2.515 0.01192 *
## xn_08 1.093718 0.470628 2.324 0.02013 *
## xa_04 -1.276047 0.665753 -1.917 0.05528 .
## xa_05 0.497786 0.231415 2.151 0.03147 *
## xa_06 0.086830 0.125676 0.691 0.48963
## xa_07 -0.234222 0.309224 -0.757 0.44878
## xa_08 0.394160 0.296777 1.328 0.18413
## xw_01 0.054832 0.029602 1.852 0.06398 .
## xw_02 0.002573 0.015807 0.163 0.87069
## xw_03 -0.053508 0.016964 -3.154 0.00161 **
## xs_01 0.998168 2.650967 0.377 0.70652
## xs_02 -2.108231 1.484366 -1.420 0.15552
## xs_03 1.639712 1.201712 1.364 0.17242
## xs_04 -2.399347 4.102694 -0.585 0.55867
## xs_05 0.370962 2.996362 0.124 0.90147
## xs_06 -0.832273 1.509090 -0.552 0.58129
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 653.59 on 676 degrees of freedom
## Residual deviance: 400.78 on 633 degrees of freedom
## AIC: 488.78
##
## Number of Fisher Scoring iterations: 7In the models with the continuous inputs, xw_03 is significant. Region ZZ, customerB, customerD, customerE ar significant in the models that contain the categorical inputs.
xw_03, Region ZZ, customerB, customerD, customerE seem to be important.
Classification Part B
Fitting Bayesian Genralized Linear Models
Model 1: glm_continuous Model 2: glm_cat_cont The reason for picking the second model is, I want to see if the categorical inputs are necessary when compared to the model with only continuous inputs and I also want to compare it to the linear regression model.
logistic_logpost <- function(unknowns, my_info)
{
X <- my_info$design_matrix
length_beta <- ncol(my_info$design_matrix)
beta_v <- unknowns[1:length_beta]
eta <- as.vector(X %*% as.matrix(beta_v))
mu <- boot::inv.logit(eta)
log_lik <- sum(dbinom(x = my_info$yobs,
size = 1,
prob = mu,
log = TRUE))
log_prior <- sum(dnorm(x =beta_v,
mean = my_info$mu_beta,
sd = my_info$tau_beta,
log = TRUE))
log_lik + log_prior
}Create Design Matrix for the two models
Xmat_cat_cont<-model.matrix( outcome~ region + customer + xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df)
Xmat_continuous <- model.matrix( outcome ~ xb_01 + xb_02 + xb_03 + xn_01 + xn_02 + xn_03 + xa_01 + xa_02 + xa_03 +xb_04 + xb_05 + xb_06 + xb_07 + xb_08 + xn_04 + xn_05 + xn_06 + xn_07 + xn_08 + xa_04 + xa_05 + xa_06 + xa_07 + xa_08 +
xw_01 + xw_02 + xw_03 + xs_01 + xs_02 + xs_03 + xs_04 + xs_05 + xs_06, data = df)df['numeric_outcome'] <- ifelse(df$outcome == 'event', 1, 0)
cat_cont_info <- list(
yobs = df$numeric_outcome,
design_matrix = Xmat_cat_cont,
mu_beta = 0,
tau_beta = 1
)
cont_info <- list(
yobs = df$numeric_outcome,
design_matrix = Xmat_continuous,
mu_beta = 0,
tau_beta = 1
)my_laplace <- function(start_guess, logpost_func, ...)
{
# code adapted from the `LearnBayes`` function `laplace()`
fit <- optim(start_guess,
logpost_func,
gr = NULL,
...,
method = "BFGS",
hessian = TRUE,
control = list(fnscale = -1, maxit = 1001))
mode <- fit$par
post_var_matrix <- -solve(fit$hessian)
p <- length(mode)
int <- p/2 * log(2 * pi) + 0.5 * log(det(post_var_matrix)) + logpost_func(mode, ...)
# package all of the results into a list
list(mode = mode,
var_matrix = post_var_matrix,
log_evidence = int,
converge = ifelse(fit$convergence == 0,
"YES",
"NO"),
iter_counts = as.numeric(fit$counts[1]))
}Execute the Laplace Approximation to fit the glm models
laplace_cat_cont <- my_laplace(rep(0,ncol(Xmat_cat_cont)), logistic_logpost, cat_cont_info)
laplace_cont <- my_laplace(rep(0,ncol(Xmat_continuous)), logistic_logpost, cont_info)Determining which model is best using Bayes Factor.
exp(laplace_cat_cont$log_evidence) / exp(laplace_cont$log_evidence)## [1] 0.723306The result of the Bayes Factor shows that there is more evidence for the continuous model, as opposed to the model with both the categorical and continuous model.
Vizualizing the regession coefficient posterior summary statsitics for the model with continuous additive inputs
viz_post_coefs(laplace_cont$mode[1:ncol(Xmat_continuous)],
sqrt(diag(laplace_cont$var_matrix)[1:ncol(Xmat_continuous)]),
colnames(Xmat_continuous))
Classifcation Part C
generate_glm_post_samples <- function(mvn_result, num_samples)
{
length_beta <- length(mvn_result$mode)
beta_samples <- MASS::mvrnorm(n = num_samples,
mu = mvn_result$mode,
Sigma = mvn_result$var_matrix)
beta_samples %>%
as.data.frame() %>% tibble::as_tibble() %>%
purrr::set_names(sprintf("beta_%02d", (1:length_beta) - 1))
}post_logistic_pred_samples <- function(Xnew, Bmat)
{
eta_mat <- Xnew %*% t(Bmat)
mu_mat <- boot::inv.logit(eta_mat)
list(eta_mat = eta_mat, mu_mat = mu_mat)
}summarize_logistic_pred_from_laplace <- function(mvn_result, Xtest, num_samples)
{
betas <- generate_glm_post_samples(mvn_result, num_samples)
betas <- as.matrix(betas)
pred_test <- post_logistic_pred_samples(Xtest, betas)
mu_avg <- rowMeans(pred_test$mu_mat)
mu_q05 <- apply(pred_test$mu_mat, 1, stats::quantile, probs = 0.05)
mu_q95 <- apply(pred_test$mu_mat, 1, stats::quantile, probs = 0.95)
tibble::tibble(
mu_avg = mu_avg,
mu_q05 = mu_q05,
mu_q95 = mu_q95
) %>%
tibble::rowid_to_column("pred_id")
}Make predictions on generated posterior samples and summarize
continuous_post_pred <- summarize_logistic_pred_from_laplace(laplace_cont, Xmat_continuous, 2500)
cat_cont_post_pred <- summarize_logistic_pred_from_laplace(laplace_cat_cont, Xmat_cat_cont, 2500)Visualize predictive trends
cat_cont_post_pred %>%
left_join(df %>% tibble::rowid_to_column("pred_id"),
by = "pred_id") %>%
mutate(event_prob = ifelse(mu_avg > 0.5, 1, 0)) %>%
ggplot(mapping = aes(x = xw_03)) +
geom_ribbon(mapping = aes(ymin = mu_q05,
ymax = mu_q95),
fill = "steelblue", alpha = 0.5) +
geom_line(mapping = aes(y = mu_avg),
color = "navyblue", size = 1.15) +
geom_point(mapping = aes(y = event_prob),
size = 2.5, alpha = 0.2) +
facet_grid(~region)
theme_bw()## List of 93
## $ line :List of 6
## ..$ colour : chr "black"
## ..$ size : num 0.5
## ..$ linetype : num 1
## ..$ lineend : chr "butt"
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ rect :List of 5
## ..$ fill : chr "white"
## ..$ colour : chr "black"
## ..$ size : num 0.5
## ..$ linetype : num 1
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ text :List of 11
## ..$ family : chr ""
## ..$ face : chr "plain"
## ..$ colour : chr "black"
## ..$ size : num 11
## ..$ hjust : num 0.5
## ..$ vjust : num 0.5
## ..$ angle : num 0
## ..$ lineheight : num 0.9
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ title : NULL
## $ aspect.ratio : NULL
## $ axis.title : NULL
## $ axis.title.x :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 2.75points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.x.top :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 2.75points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.x.bottom : NULL
## $ axis.title.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : num 90
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 2.75points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.y.left : NULL
## $ axis.title.y.right :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : num -90
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 2.75points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : chr "grey30"
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 2.2points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x.top :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 2.2points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x.bottom : NULL
## $ axis.text.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 1
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 2.2points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.y.left : NULL
## $ axis.text.y.right :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 2.2points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.ticks :List of 6
## ..$ colour : chr "grey20"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ lineend : NULL
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ axis.ticks.x : NULL
## $ axis.ticks.x.top : NULL
## $ axis.ticks.x.bottom : NULL
## $ axis.ticks.y : NULL
## $ axis.ticks.y.left : NULL
## $ axis.ticks.y.right : NULL
## $ axis.ticks.length : 'simpleUnit' num 2.75points
## ..- attr(*, "unit")= int 8
## $ axis.ticks.length.x : NULL
## $ axis.ticks.length.x.top : NULL
## $ axis.ticks.length.x.bottom: NULL
## $ axis.ticks.length.y : NULL
## $ axis.ticks.length.y.left : NULL
## $ axis.ticks.length.y.right : NULL
## $ axis.line : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.line.x : NULL
## $ axis.line.x.top : NULL
## $ axis.line.x.bottom : NULL
## $ axis.line.y : NULL
## $ axis.line.y.left : NULL
## $ axis.line.y.right : NULL
## $ legend.background :List of 5
## ..$ fill : NULL
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ legend.margin : 'margin' num [1:4] 5.5points 5.5points 5.5points 5.5points
## ..- attr(*, "unit")= int 8
## $ legend.spacing : 'simpleUnit' num 11points
## ..- attr(*, "unit")= int 8
## $ legend.spacing.x : NULL
## $ legend.spacing.y : NULL
## $ legend.key :List of 5
## ..$ fill : chr "white"
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ legend.key.size : 'simpleUnit' num 1.2lines
## ..- attr(*, "unit")= int 3
## $ legend.key.height : NULL
## $ legend.key.width : NULL
## $ legend.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ legend.text.align : NULL
## $ legend.title :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ legend.title.align : NULL
## $ legend.position : chr "right"
## $ legend.direction : NULL
## $ legend.justification : chr "center"
## $ legend.box : NULL
## $ legend.box.just : NULL
## $ legend.box.margin : 'margin' num [1:4] 0cm 0cm 0cm 0cm
## ..- attr(*, "unit")= int 1
## $ legend.box.background : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ legend.box.spacing : 'simpleUnit' num 11points
## ..- attr(*, "unit")= int 8
## $ panel.background :List of 5
## ..$ fill : chr "white"
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ panel.border :List of 5
## ..$ fill : logi NA
## ..$ colour : chr "grey20"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ panel.spacing : 'simpleUnit' num 5.5points
## ..- attr(*, "unit")= int 8
## $ panel.spacing.x : NULL
## $ panel.spacing.y : NULL
## $ panel.grid :List of 6
## ..$ colour : chr "grey92"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ lineend : NULL
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ panel.grid.major : NULL
## $ panel.grid.minor :List of 6
## ..$ colour : NULL
## ..$ size : 'rel' num 0.5
## ..$ linetype : NULL
## ..$ lineend : NULL
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ panel.grid.major.x : NULL
## $ panel.grid.major.y : NULL
## $ panel.grid.minor.x : NULL
## $ panel.grid.minor.y : NULL
## $ panel.ontop : logi FALSE
## $ plot.background :List of 5
## ..$ fill : NULL
## ..$ colour : chr "white"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ plot.title :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 1.2
## ..$ hjust : num 0
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 5.5points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.title.position : chr "panel"
## $ plot.subtitle :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 5.5points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.caption :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 0.8
## ..$ hjust : num 1
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 5.5points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.caption.position : chr "panel"
## $ plot.tag :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 1.2
## ..$ hjust : num 0.5
## ..$ vjust : num 0.5
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.tag.position : chr "topleft"
## $ plot.margin : 'margin' num [1:4] 5.5points 5.5points 5.5points 5.5points
## ..- attr(*, "unit")= int 8
## $ strip.background :List of 5
## ..$ fill : chr "grey85"
## ..$ colour : chr "grey20"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ strip.background.x : NULL
## $ strip.background.y : NULL
## $ strip.placement : chr "inside"
## $ strip.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : chr "grey10"
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 4.4points 4.4points 4.4points 4.4points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ strip.text.x : NULL
## $ strip.text.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : num -90
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ strip.switch.pad.grid : 'simpleUnit' num 2.75points
## ..- attr(*, "unit")= int 8
## $ strip.switch.pad.wrap : 'simpleUnit' num 2.75points
## ..- attr(*, "unit")= int 8
## $ strip.text.y.left :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : num 90
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## - attr(*, "class")= chr [1:2] "theme" "gg"
## - attr(*, "complete")= logi TRUE
## - attr(*, "validate")= logi TRUExn_03_vals <- pred_cont['xn_03']
min <- min(xn_03_vals)
max <- max(xn_03_vals)
mean <- (min + max) /2
med_0.25 <- (min + mean) /2
med_0.75 <- (mean + max) /2
levels <- c(min, med_0.25, mean, med_0.75, max)
levels_spaced <- rep(levels, each = nrow(df)/5)
levels_spaced[length(levels_spaced) + 1] = levels_spaced[length(levels_spaced) ]
levels_spaced[length(levels_spaced) + 1] = levels_spaced[length(levels_spaced) ]
continuous_post_pred['levels'] = as.factor(levels_spaced)
continuous_post_pred## # A tibble: 677 × 5
## pred_id mu_avg mu_q05 mu_q95 levels
## <int> <dbl> <dbl> <dbl> <fct>
## 1 1 0.00958 0.00139 0.0290 -7
## 2 2 0.0164 0.00334 0.0437 -7
## 3 3 0.110 0.0209 0.289 -7
## 4 4 0.0888 0.0227 0.210 -7
## 5 5 0.369 0.144 0.640 -7
## 6 6 0.143 0.0551 0.274 -7
## 7 7 0.483 0.173 0.805 -7
## 8 8 0.0732 0.0206 0.167 -7
## 9 9 0.236 0.0715 0.483 -7
## 10 10 0.304 0.136 0.522 -7
## # … with 667 more rowscontinuous_post_pred %>%
left_join(df %>% tibble::rowid_to_column("pred_id"),
by = "pred_id") %>%
mutate(event_prob = ifelse(mu_avg > 0.5, 1, 0)) %>%
ggplot(mapping = aes(x = xw_03)) +
geom_ribbon(mapping = aes(ymin = mu_q05,
ymax = mu_q95,
group = continuous_post_pred$levels),
fill = "steelblue", alpha = 0.5) +
geom_line(mapping = aes(y = mu_avg,
group = continuous_post_pred$levels),
color = "navyblue", size = 1.15) +
geom_point(mapping = aes(y = event_prob,
group = continuous_post_pred$levels),
size = 2.5, alpha = 0.2) +
facet_grid(~continuous_post_pred$levels)
theme_bw()## List of 93
## $ line :List of 6
## ..$ colour : chr "black"
## ..$ size : num 0.5
## ..$ linetype : num 1
## ..$ lineend : chr "butt"
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ rect :List of 5
## ..$ fill : chr "white"
## ..$ colour : chr "black"
## ..$ size : num 0.5
## ..$ linetype : num 1
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ text :List of 11
## ..$ family : chr ""
## ..$ face : chr "plain"
## ..$ colour : chr "black"
## ..$ size : num 11
## ..$ hjust : num 0.5
## ..$ vjust : num 0.5
## ..$ angle : num 0
## ..$ lineheight : num 0.9
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ title : NULL
## $ aspect.ratio : NULL
## $ axis.title : NULL
## $ axis.title.x :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 2.75points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.x.top :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 2.75points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.x.bottom : NULL
## $ axis.title.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : num 90
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 2.75points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.title.y.left : NULL
## $ axis.title.y.right :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : num -90
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 2.75points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : chr "grey30"
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 2.2points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x.top :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : num 0
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 2.2points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.x.bottom : NULL
## $ axis.text.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 1
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 2.2points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.text.y.left : NULL
## $ axis.text.y.right :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 0points 2.2points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ axis.ticks :List of 6
## ..$ colour : chr "grey20"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ lineend : NULL
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ axis.ticks.x : NULL
## $ axis.ticks.x.top : NULL
## $ axis.ticks.x.bottom : NULL
## $ axis.ticks.y : NULL
## $ axis.ticks.y.left : NULL
## $ axis.ticks.y.right : NULL
## $ axis.ticks.length : 'simpleUnit' num 2.75points
## ..- attr(*, "unit")= int 8
## $ axis.ticks.length.x : NULL
## $ axis.ticks.length.x.top : NULL
## $ axis.ticks.length.x.bottom: NULL
## $ axis.ticks.length.y : NULL
## $ axis.ticks.length.y.left : NULL
## $ axis.ticks.length.y.right : NULL
## $ axis.line : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ axis.line.x : NULL
## $ axis.line.x.top : NULL
## $ axis.line.x.bottom : NULL
## $ axis.line.y : NULL
## $ axis.line.y.left : NULL
## $ axis.line.y.right : NULL
## $ legend.background :List of 5
## ..$ fill : NULL
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ legend.margin : 'margin' num [1:4] 5.5points 5.5points 5.5points 5.5points
## ..- attr(*, "unit")= int 8
## $ legend.spacing : 'simpleUnit' num 11points
## ..- attr(*, "unit")= int 8
## $ legend.spacing.x : NULL
## $ legend.spacing.y : NULL
## $ legend.key :List of 5
## ..$ fill : chr "white"
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ legend.key.size : 'simpleUnit' num 1.2lines
## ..- attr(*, "unit")= int 3
## $ legend.key.height : NULL
## $ legend.key.width : NULL
## $ legend.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ legend.text.align : NULL
## $ legend.title :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ legend.title.align : NULL
## $ legend.position : chr "right"
## $ legend.direction : NULL
## $ legend.justification : chr "center"
## $ legend.box : NULL
## $ legend.box.just : NULL
## $ legend.box.margin : 'margin' num [1:4] 0cm 0cm 0cm 0cm
## ..- attr(*, "unit")= int 1
## $ legend.box.background : list()
## ..- attr(*, "class")= chr [1:2] "element_blank" "element"
## $ legend.box.spacing : 'simpleUnit' num 11points
## ..- attr(*, "unit")= int 8
## $ panel.background :List of 5
## ..$ fill : chr "white"
## ..$ colour : logi NA
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ panel.border :List of 5
## ..$ fill : logi NA
## ..$ colour : chr "grey20"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ panel.spacing : 'simpleUnit' num 5.5points
## ..- attr(*, "unit")= int 8
## $ panel.spacing.x : NULL
## $ panel.spacing.y : NULL
## $ panel.grid :List of 6
## ..$ colour : chr "grey92"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ lineend : NULL
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ panel.grid.major : NULL
## $ panel.grid.minor :List of 6
## ..$ colour : NULL
## ..$ size : 'rel' num 0.5
## ..$ linetype : NULL
## ..$ lineend : NULL
## ..$ arrow : logi FALSE
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_line" "element"
## $ panel.grid.major.x : NULL
## $ panel.grid.major.y : NULL
## $ panel.grid.minor.x : NULL
## $ panel.grid.minor.y : NULL
## $ panel.ontop : logi FALSE
## $ plot.background :List of 5
## ..$ fill : NULL
## ..$ colour : chr "white"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ plot.title :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 1.2
## ..$ hjust : num 0
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 5.5points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.title.position : chr "panel"
## $ plot.subtitle :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : num 0
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 0points 0points 5.5points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.caption :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 0.8
## ..$ hjust : num 1
## ..$ vjust : num 1
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 5.5points 0points 0points 0points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.caption.position : chr "panel"
## $ plot.tag :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : 'rel' num 1.2
## ..$ hjust : num 0.5
## ..$ vjust : num 0.5
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ plot.tag.position : chr "topleft"
## $ plot.margin : 'margin' num [1:4] 5.5points 5.5points 5.5points 5.5points
## ..- attr(*, "unit")= int 8
## $ strip.background :List of 5
## ..$ fill : chr "grey85"
## ..$ colour : chr "grey20"
## ..$ size : NULL
## ..$ linetype : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_rect" "element"
## $ strip.background.x : NULL
## $ strip.background.y : NULL
## $ strip.placement : chr "inside"
## $ strip.text :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : chr "grey10"
## ..$ size : 'rel' num 0.8
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : NULL
## ..$ lineheight : NULL
## ..$ margin : 'margin' num [1:4] 4.4points 4.4points 4.4points 4.4points
## .. ..- attr(*, "unit")= int 8
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ strip.text.x : NULL
## $ strip.text.y :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : num -90
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## $ strip.switch.pad.grid : 'simpleUnit' num 2.75points
## ..- attr(*, "unit")= int 8
## $ strip.switch.pad.wrap : 'simpleUnit' num 2.75points
## ..- attr(*, "unit")= int 8
## $ strip.text.y.left :List of 11
## ..$ family : NULL
## ..$ face : NULL
## ..$ colour : NULL
## ..$ size : NULL
## ..$ hjust : NULL
## ..$ vjust : NULL
## ..$ angle : num 90
## ..$ lineheight : NULL
## ..$ margin : NULL
## ..$ debug : NULL
## ..$ inherit.blank: logi TRUE
## ..- attr(*, "class")= chr [1:2] "element_text" "element"
## - attr(*, "class")= chr [1:2] "theme" "gg"
## - attr(*, "complete")= logi TRUE
## - attr(*, "validate")= logi TRUEThe predictive trends are somewhat consistent between the two models. When xw_03 ≥ 60 there is a higher chance that the predicted class is event. When xw_03 is between 30 and 60 it is more likely that the class predicted is a non-event.
Classification - Part D
Training, Tuning, Evaluation Generalized Linear Models
df_class <- df %>%
select(region, customer, starts_with('x'), outcome)metric_acc <- "Accuracy"
my_ctrl_acc <- trainControl(method = "repeatedcv" , number = 5, repeats = 5, metric_acc, classProbs = TRUE)
my_ctrl_roc <- trainControl(method = "repeatedcv" , number = 5, repeats = 5, summaryFunction = twoClassSummary, classProbs = TRUE)cat_cont_tune_acc <- caret::train(outcome ~ ., data = df_class, method = 'glm' , metric = metric_acc,
preProcess = c('center','scale'), trControl = my_ctrl_acc)## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredcat_cont_tune_roc <- caret::train(outcome ~ ., data = df_class, method = 'glm' ,
preProcess = c('center','scale'), trControl = my_ctrl_roc)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.
## Warning in train.default(x, y, weights = w, ...): glm.fit: fitted probabilities
## numerically 0 or 1 occurredAll pairwise interactions of continuous inputs and additive categorical features
pairwise_tune_acc <- caret::train(outcome ~ (.)^2 + region + customer ,data = df_class, method = 'glm', metric = metric_acc,
preProcess = c('center','scale'), trControl = my_ctrl_acc)## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredpairwise_tune_roc <- caret::train(outcome ~ (.)^2 + region + customer ,data = df_class, method = 'glm',
preProcess = c('center','scale'), trControl = my_ctrl_roc)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: algorithm did not converge## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading
## Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
## prediction from a rank-deficient fit may be misleading## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredTraining the second model from Regression Part A (mod_continuous)
Second model from Part A is the same as the cat_cont_tune
continuous_tune_acc <- caret::train(outcome ~ .,data = df_class, method = 'glm', metric = metric_acc,
preProcess = c('center','scale'), trControl = my_ctrl_acc)## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredcontinuous_tune_roc <- caret::train(outcome ~ .,data = df_class, method = 'glm',
preProcess = c('center','scale'), trControl = my_ctrl_roc)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.Regularized Logistic Regression with Elastic Net
All pairwise interactions of continuous inputs, including categorical features
pairwise_tune_acc_enet <- caret::train(outcome ~ (.)^2 + region + customer ,data = df_class, method = 'glmnet', metric = metric_acc,
preProcess = c('center','scale'), trControl = my_ctrl_acc)## Warning in preProcess.default(method = c("center", "scale"), x =
## structure(c(0, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQpairwise_tune_roc_enet <- caret::train(outcome ~ (.)^2 + region + customer ,data = df_class, method = 'glmnet',
preProcess = c('center','scale'), trControl = my_ctrl_roc)## Warning in preProcess.default(method = c("center", "scale"), x =
## structure(c(0, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQ## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19,
## uniqueCut = 10, : These variables have zero variances: regionZZ:customerB,
## regionZZ:customerD, regionZZ:customerE, regionYY:customerG, regionYY:customerK,
## regionYY:customerM, regionZZ:customerQMore complex of the top two models - Categorical + Continuous inputs
cat_cont_tune_acc_enet <- caret::train(outcome ~ ., data = df_class, method = 'glmnet' , metric = metric_acc,
preProcess = c('center','scale'), trControl = my_ctrl_acc)
cat_cont_tune_roc_enet <- caret::train(outcome ~ ., data = df_class, method = 'glmnet' ,
preProcess = c('center','scale'), trControl = my_ctrl_roc)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.Using Neural Network to Train, evaluate, and tune the glm_cat_cont model.
set.seed(4321)
fit_nnet_acc <- train(outcome ~ .,
data = df_class, method = "nnet", metric = metric_acc, trControl = my_ctrl_roc,
preProcess = c('center', 'scale'),
trace = FALSE)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.fit_nnet_roc <- train(outcome ~ .,
data = df_class, method = "nnet", trControl = my_ctrl_roc,
preProcess = c('center', 'scale'),
trace = FALSE)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.Using Random Forest to Train, evaluate, and tune the glm_cat_cont model.
set.seed(4321)
fit_rf_acc <- train(outcome ~ .,
data = df_class, method = "rf", metric = metric_acc, trControl = my_ctrl_acc ,trace = FALSE)
fit_rf_roc <- train(outcome ~ .,
data = df_class, method = "rf", trControl = my_ctrl_roc ,trace = FALSE)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.Using Extrem Gradient Boosted Tree to Train, evaluate, and tune the glm_cat_cont model.
set.seed(4321)
fit_xgb_acc <- train(outcome ~ .,
data = df_class, method = 'xgbTree', metric = metric_acc, trControl = my_ctrl_acc, preProcess = c('center', 'scale'), verbosity = 0)
fit_xgb_roc <- train(outcome ~ .,
data = df_class, method = 'xgbTree', trControl = my_ctrl_roc, preProcess = c('center', 'scale'), verbosity = 0)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.Using SVM to Train, evaluate, and tune the glm_cat_cont model.
set.seed(4321)
fit_pls_acc <- train(outcome ~ ., data = df_class, method = "pls", metric = metric_acc,
trControl = my_ctrl_acc,
preProcess = c('center', 'scale'),
trace = FALSE)
fit_pls_roc <- train(outcome ~ .,
data = df_class, method = "pls", trControl = my_ctrl_roc,
preProcess = c('center', 'scale'), importance = TRUE,
trace = FALSE)## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.Using KNN to Train, evaluate, and tune the glm_cat_cont model.
fit_knn_acc <- train(outcome ~ .,
data = df_class, method = "knn", metric = metric_acc, trControl = my_ctrl_acc,
preProcess = c('center', 'scale'))
fit_knn_roc <- train(outcome ~ .,
data = df_class, method = "knn", trControl = my_ctrl_roc,
preProcess = c('center', 'scale'))## Warning in train.default(x, y, weights = w, ...): The metric "Accuracy" was not
## in the result set. ROC will be used instead.cat_cont_tune_acc## Generalized Linear Model
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 542, 542, 541, 542, 542, ...
## Resampling results:
##
## Accuracy Kappa
## 0.8369368 0.4061143pairwise_tune_acc## Generalized Linear Model
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (917), scaled (917)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 541, 542, 542, 541, 541, ...
## Resampling results:
##
## Accuracy Kappa
## 0.5090436 0.01971732pairwise_tune_acc_enet## glmnet
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (917), scaled (917)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 542, 542, 541, 541, 542, ...
## Resampling results across tuning parameters:
##
## alpha lambda Accuracy Kappa
## 0.10 0.01039198 0.8088497 0.287327941
## 0.10 0.03286232 0.8221373 0.308150217
## 0.10 0.10391977 0.8259804 0.244211871
## 0.55 0.01039198 0.8197712 0.297273152
## 0.55 0.03286232 0.8271612 0.241654299
## 0.55 0.10391977 0.8189194 0.089376004
## 1.00 0.01039198 0.8242070 0.282578860
## 1.00 0.03286232 0.8230305 0.194994095
## 1.00 0.10391977 0.8133072 0.007630058
##
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were alpha = 0.55 and lambda = 0.03286232.fit_nnet_acc## Neural Network
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 542, 541, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## size decay ROC Sens Spec
## 1 0e+00 0.7299463 0.4419692 0.8414545
## 1 1e-04 0.7554853 0.6216000 0.7880000
## 1 1e-01 0.8268397 0.4904000 0.8920000
## 3 0e+00 0.7655530 0.4824000 0.8596364
## 3 1e-04 0.7743127 0.4729846 0.8683636
## 3 1e-01 0.7837874 0.4319385 0.8687273
## 5 0e+00 0.7763231 0.4894769 0.8625455
## 5 1e-04 0.7778305 0.4776615 0.8720000
## 5 1e-01 0.7800604 0.4078769 0.8720000
##
## ROC was used to select the optimal model using the largest value.
## The final values used for the model were size = 1 and decay = 0.1.fit_rf_acc## Random Forest
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 542, 541, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## mtry Accuracy Kappa
## 2 0.8203856 0.2130003
## 22 0.8082919 0.2526457
## 43 0.8065185 0.2544518
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 2.fit_xgb_acc## eXtreme Gradient Boosting
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 542, 541, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## eta max_depth colsample_bytree subsample nrounds Accuracy Kappa
## 0.3 1 0.6 0.50 50 0.8130000 0.2823817
## 0.3 1 0.6 0.50 100 0.8076863 0.2773012
## 0.3 1 0.6 0.50 150 0.7967538 0.2570461
## 0.3 1 0.6 0.75 50 0.8091656 0.2613077
## 0.3 1 0.6 0.75 100 0.8082658 0.2670792
## 0.3 1 0.6 0.75 150 0.8038235 0.2605973
## 0.3 1 0.6 1.00 50 0.8103529 0.2315027
## 0.3 1 0.6 1.00 100 0.8085708 0.2433223
## 0.3 1 0.6 1.00 150 0.8091503 0.2621768
## 0.3 1 0.8 0.50 50 0.8132919 0.2884634
## 0.3 1 0.8 0.50 100 0.8050044 0.2739623
## 0.3 1 0.8 0.50 150 0.7946797 0.2402142
## 0.3 1 0.8 0.75 50 0.8174444 0.2926027
## 0.3 1 0.8 0.75 100 0.8100414 0.2780364
## 0.3 1 0.8 0.75 150 0.8032462 0.2570141
## 0.3 1 0.8 1.00 50 0.8121285 0.2418932
## 0.3 1 0.8 1.00 100 0.8097538 0.2537657
## 0.3 1 0.8 1.00 150 0.8097429 0.2613991
## 0.3 2 0.6 0.50 50 0.8003007 0.2569425
## 0.3 2 0.6 0.50 100 0.7958824 0.2573299
## 0.3 2 0.6 0.50 150 0.7926318 0.2514879
## 0.3 2 0.6 0.75 50 0.8029586 0.2606482
## 0.3 2 0.6 0.75 100 0.7920174 0.2328071
## 0.3 2 0.6 0.75 150 0.7905468 0.2271942
## 0.3 2 0.6 1.00 50 0.8053159 0.2479008
## 0.3 2 0.6 1.00 100 0.7982135 0.2433879
## 0.3 2 0.6 1.00 150 0.7952658 0.2428139
## 0.3 2 0.8 0.50 50 0.8023638 0.2698115
## 0.3 2 0.8 0.50 100 0.7961699 0.2542804
## 0.3 2 0.8 0.50 150 0.7935011 0.2563295
## 0.3 2 0.8 0.75 50 0.7982353 0.2416338
## 0.3 2 0.8 0.75 100 0.7946906 0.2490171
## 0.3 2 0.8 0.75 150 0.7887821 0.2368030
## 0.3 2 0.8 1.00 50 0.8014771 0.2335315
## 0.3 2 0.8 1.00 100 0.7955577 0.2328083
## 0.3 2 0.8 1.00 150 0.7896449 0.2258429
## 0.3 3 0.6 0.50 50 0.8050131 0.2670057
## 0.3 3 0.6 0.50 100 0.7946732 0.2375245
## 0.3 3 0.6 0.50 150 0.7934815 0.2369197
## 0.3 3 0.6 0.75 50 0.8005817 0.2531733
## 0.3 3 0.6 0.75 100 0.7952593 0.2463800
## 0.3 3 0.6 0.75 150 0.7984989 0.2667216
## 0.3 3 0.6 1.00 50 0.7946819 0.2381066
## 0.3 3 0.6 1.00 100 0.7937778 0.2299837
## 0.3 3 0.6 1.00 150 0.7926057 0.2336673
## 0.3 3 0.8 0.50 50 0.8044379 0.2715835
## 0.3 3 0.8 0.50 100 0.7946863 0.2480306
## 0.3 3 0.8 0.50 150 0.7949804 0.2457518
## 0.3 3 0.8 0.75 50 0.7926187 0.2216252
## 0.3 3 0.8 0.75 100 0.7929259 0.2308439
## 0.3 3 0.8 0.75 150 0.7935120 0.2332497
## 0.3 3 0.8 1.00 50 0.8023660 0.2559682
## 0.3 3 0.8 1.00 100 0.7988105 0.2468088
## 0.3 3 0.8 1.00 150 0.7979216 0.2513858
## 0.4 1 0.6 0.50 50 0.8067952 0.2750498
## 0.4 1 0.6 0.50 100 0.8038584 0.2589239
## 0.4 1 0.6 0.50 150 0.8038519 0.2834329
## 0.4 1 0.6 0.75 50 0.8112418 0.2776025
## 0.4 1 0.6 0.75 100 0.8020828 0.2621478
## 0.4 1 0.6 0.75 150 0.7973508 0.2458121
## 0.4 1 0.6 1.00 50 0.8109455 0.2508713
## 0.4 1 0.6 1.00 100 0.8094510 0.2615937
## 0.4 1 0.6 1.00 150 0.8070959 0.2655213
## 0.4 1 0.8 0.50 50 0.8124227 0.2999567
## 0.4 1 0.8 0.50 100 0.7970523 0.2584186
## 0.4 1 0.8 0.50 150 0.7973617 0.2529232
## 0.4 1 0.8 0.75 50 0.8056340 0.2440220
## 0.4 1 0.8 0.75 100 0.8017843 0.2430125
## 0.4 1 0.8 0.75 150 0.7979455 0.2397753
## 0.4 1 0.8 1.00 50 0.8130218 0.2587003
## 0.4 1 0.8 1.00 100 0.8088627 0.2615008
## 0.4 1 0.8 1.00 150 0.8056078 0.2582943
## 0.4 2 0.6 0.50 50 0.7949869 0.2465330
## 0.4 2 0.6 0.50 100 0.7870174 0.2312048
## 0.4 2 0.6 0.50 150 0.7896667 0.2442424
## 0.4 2 0.6 0.75 50 0.7967342 0.2580543
## 0.4 2 0.6 0.75 100 0.7970414 0.2687535
## 0.4 2 0.6 0.75 150 0.7940806 0.2472883
## 0.4 2 0.6 1.00 50 0.7996885 0.2401947
## 0.4 2 0.6 1.00 100 0.7949455 0.2440420
## 0.4 2 0.6 1.00 150 0.7958410 0.2487236
## 0.4 2 0.8 0.50 50 0.7961634 0.2573260
## 0.4 2 0.8 0.50 100 0.7952919 0.2586614
## 0.4 2 0.8 0.50 150 0.7935185 0.2648670
## 0.4 2 0.8 0.75 50 0.8017647 0.2640843
## 0.4 2 0.8 0.75 100 0.7925904 0.2527595
## 0.4 2 0.8 0.75 150 0.7884532 0.2448207
## 0.4 2 0.8 1.00 50 0.8014662 0.2481301
## 0.4 2 0.8 1.00 100 0.7899586 0.2290135
## 0.4 2 0.8 1.00 150 0.7902593 0.2343891
## 0.4 3 0.6 0.50 50 0.8014967 0.2637866
## 0.4 3 0.6 0.50 100 0.7979303 0.2583711
## 0.4 3 0.6 0.50 150 0.7994074 0.2598881
## 0.4 3 0.6 0.75 50 0.8035599 0.2749628
## 0.4 3 0.6 0.75 100 0.7946885 0.2454333
## 0.4 3 0.6 0.75 150 0.7982309 0.2517559
## 0.4 3 0.6 1.00 50 0.7970370 0.2439013
## 0.4 3 0.6 1.00 100 0.8002789 0.2552603
## 0.4 3 0.6 1.00 150 0.7982179 0.2567209
## 0.4 3 0.8 0.50 50 0.7940980 0.2425109
## 0.4 3 0.8 0.50 100 0.8011721 0.2776495
## 0.4 3 0.8 0.50 150 0.8026427 0.2862123
## 0.4 3 0.8 0.75 50 0.7929129 0.2396934
## 0.4 3 0.8 0.75 100 0.7935054 0.2445333
## 0.4 3 0.8 0.75 150 0.7931983 0.2478071
## 0.4 3 0.8 1.00 50 0.7982092 0.2458159
## 0.4 3 0.8 1.00 100 0.7988083 0.2548772
## 0.4 3 0.8 1.00 150 0.7982135 0.2532278
##
## Tuning parameter 'gamma' was held constant at a value of 0
## Tuning
## parameter 'min_child_weight' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were nrounds = 50, max_depth = 1, eta
## = 0.3, gamma = 0, colsample_bytree = 0.8, min_child_weight = 1 and subsample
## = 0.75.fit_pls_acc## Partial Least Squares
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 542, 541, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## ncomp Accuracy Kappa
## 1 0.8236558 0.1531122
## 2 0.8263246 0.2107718
## 3 0.8277930 0.1962398
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was ncomp = 3.fit_knn_acc## k-Nearest Neighbors
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 542, 541, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## k Accuracy Kappa
## 5 0.8115163 0.2568544
## 7 0.8197865 0.2703851
## 9 0.8194989 0.2505884
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was k = 7.cat_cont_tune_roc## Generalized Linear Model
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 541, 542, 542, 542, 542, ...
## Resampling results:
##
## ROC Sens Spec
## 0.8320599 0.4379692 0.932pairwise_tune_roc## Generalized Linear Model
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (917), scaled (917)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 541, 542, 542, 541, 541, ...
## Resampling results:
##
## ROC Sens Spec
## 0.5060948 0.4865231 0.5221818pairwise_tune_roc_enet## glmnet
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (917), scaled (917)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 541, 542, 541, 542, 541, ...
## Resampling results across tuning parameters:
##
## alpha lambda ROC Sens Spec
## 0.10 0.01039198 0.8020699 0.3480615 0.9192727
## 0.10 0.03286232 0.8194154 0.3244923 0.9349091
## 0.10 0.10391977 0.8433331 0.2360615 0.9647273
## 0.55 0.01039198 0.8174316 0.3273846 0.9349091
## 0.55 0.03286232 0.8468319 0.2188923 0.9690909
## 0.55 0.10391977 0.8389866 0.0648000 0.9923636
## 1.00 0.01039198 0.8326730 0.2817231 0.9520000
## 1.00 0.03286232 0.8447748 0.1735385 0.9749091
## 1.00 0.10391977 0.8239122 0.0032000 1.0000000
##
## ROC was used to select the optimal model using the largest value.
## The final values used for the model were alpha = 0.55 and lambda = 0.03286232.fit_nnet_roc## Neural Network
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 542, 542, 541, 542, 541, ...
## Resampling results across tuning parameters:
##
## size decay ROC Sens Spec
## 1 0e+00 0.7342764 0.6107077 0.7843636
## 1 1e-04 0.7569891 0.6452923 0.7712727
## 1 1e-01 0.8318870 0.5019077 0.8989091
## 3 0e+00 0.7674638 0.5105231 0.8578182
## 3 1e-04 0.7776050 0.4545231 0.8767273
## 3 1e-01 0.7873594 0.4316923 0.8807273
## 5 0e+00 0.7622722 0.4688615 0.8698182
## 5 1e-04 0.7536008 0.4550769 0.8632727
## 5 1e-01 0.7835933 0.4256000 0.8730909
##
## ROC was used to select the optimal model using the largest value.
## The final values used for the model were size = 1 and decay = 0.1.fit_rf_roc ## Random Forest
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## No pre-processing
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 541, 542, 542, 542, 542, ...
## Resampling results across tuning parameters:
##
## mtry ROC Sens Spec
## 2 0.8316719 0.2164308 0.9600000
## 22 0.8213407 0.3072615 0.9287273
## 43 0.8137200 0.3214154 0.9272727
##
## ROC was used to select the optimal model using the largest value.
## The final value used for the model was mtry = 2.fit_xgb_roc## eXtreme Gradient Boosting
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 542, 542, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## eta max_depth colsample_bytree subsample nrounds ROC Sens
## 0.3 1 0.6 0.50 50 0.8163639 0.3356923
## 0.3 1 0.6 0.50 100 0.8042148 0.3408000
## 0.3 1 0.6 0.50 150 0.7915357 0.3409846
## 0.3 1 0.6 0.75 50 0.8197373 0.3057231
## 0.3 1 0.6 0.75 100 0.8065483 0.3264615
## 0.3 1 0.6 0.75 150 0.7985326 0.3185846
## 0.3 1 0.6 1.00 50 0.8203024 0.2416000
## 0.3 1 0.6 1.00 100 0.8148503 0.2743385
## 0.3 1 0.6 1.00 150 0.8084112 0.3072615
## 0.3 1 0.8 0.50 50 0.8130971 0.3230769
## 0.3 1 0.8 0.50 100 0.8020526 0.3216615
## 0.3 1 0.8 0.50 150 0.7969348 0.3200000
## 0.3 1 0.8 0.75 50 0.8177116 0.3043692
## 0.3 1 0.8 0.75 100 0.8055250 0.3123692
## 0.3 1 0.8 0.75 150 0.7981494 0.3187692
## 0.3 1 0.8 1.00 50 0.8212173 0.2619692
## 0.3 1 0.8 1.00 100 0.8135105 0.2806154
## 0.3 1 0.8 1.00 150 0.8087681 0.2900923
## 0.3 2 0.6 0.50 50 0.7971603 0.3218462
## 0.3 2 0.6 0.50 100 0.7817538 0.3297231
## 0.3 2 0.6 0.50 150 0.7730697 0.3329846
## 0.3 2 0.6 0.75 50 0.8071390 0.3515692
## 0.3 2 0.6 0.75 100 0.7937007 0.3358769
## 0.3 2 0.6 0.75 150 0.7878456 0.3499077
## 0.3 2 0.6 1.00 50 0.8063429 0.3029538
## 0.3 2 0.6 1.00 100 0.7942081 0.3203692
## 0.3 2 0.6 1.00 150 0.7866294 0.3294769
## 0.3 2 0.8 0.50 50 0.8042143 0.3377231
## 0.3 2 0.8 0.50 100 0.7908201 0.3376615
## 0.3 2 0.8 0.50 150 0.7824727 0.3360000
## 0.3 2 0.8 0.75 50 0.8011345 0.3157538
## 0.3 2 0.8 0.75 100 0.7881029 0.3361231
## 0.3 2 0.8 0.75 150 0.7839787 0.3360615
## 0.3 2 0.8 1.00 50 0.8019323 0.3011077
## 0.3 2 0.8 1.00 100 0.7891262 0.3123692
## 0.3 2 0.8 1.00 150 0.7852929 0.3252308
## 0.3 3 0.6 0.50 50 0.7970478 0.3452308
## 0.3 3 0.6 0.50 100 0.7829975 0.3404308
## 0.3 3 0.6 0.50 150 0.7768895 0.3511385
## 0.3 3 0.6 0.75 50 0.8006786 0.3465231
## 0.3 3 0.6 0.75 100 0.7849180 0.3324923
## 0.3 3 0.6 0.75 150 0.7811905 0.3452308
## 0.3 3 0.6 1.00 50 0.7944369 0.2950154
## 0.3 3 0.6 1.00 100 0.7857499 0.3094769
## 0.3 3 0.6 1.00 150 0.7809706 0.3172923
## 0.3 3 0.8 0.50 50 0.7891653 0.3472615
## 0.3 3 0.8 0.50 100 0.7812319 0.3392615
## 0.3 3 0.8 0.50 150 0.7769768 0.3392000
## 0.3 3 0.8 0.75 50 0.7954982 0.3422769
## 0.3 3 0.8 0.75 100 0.7901572 0.3329231
## 0.3 3 0.8 0.75 150 0.7838014 0.3265846
## 0.3 3 0.8 1.00 50 0.7976207 0.3059077
## 0.3 3 0.8 1.00 100 0.7847972 0.2995692
## 0.3 3 0.8 1.00 150 0.7804973 0.3137846
## 0.4 1 0.6 0.50 50 0.8074408 0.3388308
## 0.4 1 0.6 0.50 100 0.7936481 0.3468923
## 0.4 1 0.6 0.50 150 0.7897617 0.3438769
## 0.4 1 0.6 0.75 50 0.8115804 0.2966154
## 0.4 1 0.6 0.75 100 0.8028906 0.3310154
## 0.4 1 0.6 0.75 150 0.7919748 0.3295385
## 0.4 1 0.6 1.00 50 0.8174490 0.2731077
## 0.4 1 0.6 1.00 100 0.8109941 0.2932308
## 0.4 1 0.6 1.00 150 0.8024593 0.3137846
## 0.4 1 0.8 0.50 50 0.8000761 0.3313231
## 0.4 1 0.8 0.50 100 0.7939866 0.3686769
## 0.4 1 0.8 0.50 150 0.7757427 0.3435077
## 0.4 1 0.8 0.75 50 0.8116543 0.3153231
## 0.4 1 0.8 0.75 100 0.7943575 0.3033231
## 0.4 1 0.8 0.75 150 0.7894042 0.3126154
## 0.4 1 0.8 1.00 50 0.8166498 0.2650462
## 0.4 1 0.8 1.00 100 0.8088453 0.2979077
## 0.4 1 0.8 1.00 150 0.8038971 0.3212308
## 0.4 2 0.6 0.50 50 0.7763021 0.3196923
## 0.4 2 0.6 0.50 100 0.7719894 0.3342769
## 0.4 2 0.6 0.50 150 0.7657650 0.3451692
## 0.4 2 0.6 0.75 50 0.7817248 0.3028308
## 0.4 2 0.6 0.75 100 0.7753264 0.3127385
## 0.4 2 0.6 0.75 150 0.7706853 0.3110769
## 0.4 2 0.6 1.00 50 0.7922378 0.2916923
## 0.4 2 0.6 1.00 100 0.7821857 0.3120615
## 0.4 2 0.6 1.00 150 0.7763765 0.3199385
## 0.4 2 0.8 0.50 50 0.7859312 0.3582154
## 0.4 2 0.8 0.50 100 0.7732050 0.3438154
## 0.4 2 0.8 0.50 150 0.7687452 0.3473846
## 0.4 2 0.8 0.75 50 0.7935401 0.3362462
## 0.4 2 0.8 0.75 100 0.7869555 0.3392000
## 0.4 2 0.8 0.75 150 0.7784699 0.3455385
## 0.4 2 0.8 1.00 50 0.7963457 0.3123077
## 0.4 2 0.8 1.00 100 0.7843916 0.3139692
## 0.4 2 0.8 1.00 150 0.7761617 0.3315077
## 0.4 3 0.6 0.50 50 0.7807401 0.3563692
## 0.4 3 0.6 0.50 100 0.7770081 0.3648615
## 0.4 3 0.6 0.50 150 0.7727759 0.3617846
## 0.4 3 0.6 0.75 50 0.7854344 0.3392000
## 0.4 3 0.6 0.75 100 0.7789303 0.3344000
## 0.4 3 0.6 0.75 150 0.7762081 0.3296615
## 0.4 3 0.6 1.00 50 0.7851877 0.3391385
## 0.4 3 0.6 1.00 100 0.7768917 0.3172308
## 0.4 3 0.6 1.00 150 0.7743211 0.3171692
## 0.4 3 0.8 0.50 50 0.7796878 0.3373538
## 0.4 3 0.8 0.50 100 0.7719944 0.3563077
## 0.4 3 0.8 0.50 150 0.7686378 0.3438154
## 0.4 3 0.8 0.75 50 0.7856481 0.3249846
## 0.4 3 0.8 0.75 100 0.7787189 0.3315077
## 0.4 3 0.8 0.75 150 0.7756694 0.3331692
## 0.4 3 0.8 1.00 50 0.7922920 0.3247385
## 0.4 3 0.8 1.00 100 0.7859144 0.3281231
## 0.4 3 0.8 1.00 150 0.7792828 0.3374154
## Spec
## 0.9356364
## 0.9203636
## 0.9123636
## 0.9363636
## 0.9203636
## 0.9160000
## 0.9429091
## 0.9352727
## 0.9312727
## 0.9330909
## 0.9312727
## 0.9261818
## 0.9356364
## 0.9218182
## 0.9152727
## 0.9410909
## 0.9345455
## 0.9316364
## 0.9170909
## 0.9036364
## 0.9025455
## 0.9221818
## 0.9094545
## 0.9061818
## 0.9280000
## 0.9163636
## 0.9101818
## 0.9225455
## 0.9098182
## 0.9040000
## 0.9218182
## 0.9098182
## 0.9069091
## 0.9287273
## 0.9160000
## 0.9054545
## 0.9149091
## 0.9156364
## 0.9120000
## 0.9178182
## 0.9112727
## 0.9112727
## 0.9218182
## 0.9156364
## 0.9134545
## 0.9174545
## 0.9087273
## 0.9069091
## 0.9120000
## 0.9076364
## 0.9083636
## 0.9200000
## 0.9149091
## 0.9127273
## 0.9272727
## 0.9090909
## 0.9025455
## 0.9298182
## 0.9229091
## 0.9141818
## 0.9385455
## 0.9330909
## 0.9243636
## 0.9247273
## 0.9080000
## 0.9014545
## 0.9287273
## 0.9127273
## 0.9076364
## 0.9392727
## 0.9305455
## 0.9236364
## 0.9014545
## 0.8978182
## 0.8970909
## 0.9087273
## 0.8967273
## 0.8989091
## 0.9178182
## 0.9116364
## 0.9105455
## 0.9090909
## 0.9058182
## 0.9069091
## 0.9141818
## 0.9080000
## 0.9043636
## 0.9236364
## 0.9112727
## 0.9072727
## 0.9018182
## 0.9036364
## 0.9029091
## 0.9050909
## 0.9083636
## 0.9040000
## 0.9101818
## 0.9105455
## 0.9127273
## 0.9080000
## 0.9072727
## 0.9083636
## 0.9109091
## 0.9061818
## 0.9087273
## 0.9163636
## 0.9101818
## 0.9141818
##
## Tuning parameter 'gamma' was held constant at a value of 0
## Tuning
## parameter 'min_child_weight' was held constant at a value of 1
## ROC was used to select the optimal model using the largest value.
## The final values used for the model were nrounds = 50, max_depth = 1, eta
## = 0.3, gamma = 0, colsample_bytree = 0.8, min_child_weight = 1 and subsample
## = 1.fit_pls_roc## Partial Least Squares
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 542, 541, 542, 542, 541, 541, ...
## Resampling results across tuning parameters:
##
## ncomp ROC Sens Spec
## 1 0.8094193 0.1257846 0.9836364
## 2 0.8323234 0.1921231 0.9745455
## 3 0.8428850 0.1668923 0.9836364
##
## ROC was used to select the optimal model using the largest value.
## The final value used for the model was ncomp = 3.fit_knn_roc## k-Nearest Neighbors
##
## 677 samples
## 35 predictor
## 2 classes: 'event', 'non_event'
##
## Pre-processing: centered (43), scaled (43)
## Resampling: Cross-Validated (5 fold, repeated 5 times)
## Summary of sample sizes: 541, 542, 542, 542, 541, 542, ...
## Resampling results across tuning parameters:
##
## k ROC Sens Spec
## 5 0.7182420 0.2774769 0.9363636
## 7 0.7436666 0.2726769 0.9520000
## 9 0.7636523 0.2425846 0.9534545
##
## ROC was used to select the optimal model using the largest value.
## The final value used for the model was k = 9.The model that maximizes the accuracy is the categorical and continuous inputs trained through partial least squares. The model that maximizes the ROC is also the categorical and continuous inputs trained through partial least squares.
Interpretation - Part A
- When trained, tuned, and evaluated the best model is The pairwise interactions tuned through elastic net.
- For the classification models, the model that was selected based on Accuracy and AUC ROC is the model with the categoerical and continuous inputs trained via Partial Least Squares.
Identifying the most important variables associated with the best performing regression and classification models
plot(varImp(pairwise_enet), top = 5)
plot(varImp(fit_pls_acc), top = 5)##
## Attaching package: 'pls'## The following object is masked from 'package:caret':
##
## R2## The following object is masked from 'package:stats':
##
## loadings
For the regression pairwise model tuned through elastic net xw_01 is the most important variable. For the classification RF, the most important variable is xn_01
The important features between the regression and classification models are not very consistent with each other.
The model results are okay. They had a very high performance on the test metric but I feel as though based on that and the sentiment contributions, that they are not actually that useful. It seems that the most important feature is the response type.
Read in Hold-out set
holdout <- readr::read_csv('final_project_holdout_inputs.csv', col_names = TRUE)## Rows: 73 Columns: 36
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): region, customer
## dbl (34): rowid, xb_01, xb_02, xb_03, xn_01, xn_02, xn_03, xa_01, xa_02, xa_...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.holdout_inputs <- holdout %>%
select(-rowid)Predict using Pairwise Elastic Net - Regression
predict_reg <- predict(pairwise_enet, holdout_inputs)Predict using Partial Least Squares - Classification
predict_class <- predict(fit_pls_acc, holdout_inputs)
predict_class_prob <- predict(fit_pls_acc, holdout_inputs, type = 'prob')
head(predict_class_prob)## event non_event
## 1 0.4209747 0.5790253
## 2 0.3823736 0.6176264
## 3 0.2707591 0.7292409
## 4 0.4532684 0.5467316
## 5 0.3665141 0.6334859
## 6 0.3053693 0.6946307Compile Predictions
my_preds <- tibble::tibble(
y = predict_reg,
outcome = predict_class
) %>%
bind_cols(
predict_class_prob %>%
select(probability = event)
) %>%
tibble::rowid_to_column('id')
head(my_preds)## # A tibble: 6 × 4
## id y outcome probability
## <int> <dbl> <fct> <dbl>
## 1 1 0.450 non_event 0.421
## 2 2 0.874 non_event 0.382
## 3 3 1.13 non_event 0.271
## 4 4 0.924 non_event 0.453
## 5 5 0.492 non_event 0.367
## 6 6 0.336 non_event 0.305my_preds %>%
readr::write_csv('Boppana_Sameera_preds.csv', col_names = TRUE)Determining the hardest customer to predict
holdout$predict_reg <- predict_reg
holdout$predict_class <- predict_class
customer <- data.frame(cbind(holdout$customer, holdout$predict_reg, holdout$predict_class))
colnames(customer) <- c("customer", "pred_reg", "pred_class")
customer <- customer %>% mutate(pred_class = ifelse(pred_class == 2, "non_event", "event"))
customer$true_class <- ifelse(predict_reg > 0.5, "event", "non_event")
customer %>% group_by(customer) %>%
count(pred_class == true_class)## # A tibble: 13 × 3
## # Groups: customer [8]
## customer `pred_class == true_class` n
## <chr> <lgl> <int>
## 1 A FALSE 8
## 2 A TRUE 2
## 3 B FALSE 4
## 4 D FALSE 2
## 5 E FALSE 3
## 6 E TRUE 1
## 7 G FALSE 7
## 8 G TRUE 5
## 9 M FALSE 4
## 10 M TRUE 3
## 11 Other FALSE 25
## 12 Other TRUE 6
## 13 Q FALSE 3The most amount of missclassifications is from Customer “Other”. Since this customer group had the most amount of missclassications, this is the hardest customer to predict.
Visuzaling prediction trends with the hardest to classify customer group (Other) with the most important derived feature xn_01
hardest_customer <- holdout[holdout$customer == 'Other',]
xn_01_vals <- hardest_customer['xn_01']
min <- min(xn_01_vals)
max <- max(xn_01_vals)
mean <- (min + max) /2
med_0.25 <- (min + mean) /2
med_0.75 <- (mean + max) /2
levels <- c(min, med_0.25, mean, med_0.75, max)
levels_spaced <- rep(levels, each = nrow(hardest_customer)/5)
levels_spaced[length(levels_spaced) ] = levels_spaced[length(levels_spaced) ]
levels_spaced[length(levels_spaced) +1] = levels_spaced[length(levels_spaced) ]
hardest_customer['levels'] = as.factor(levels_spaced)
hardest_customer %>%
ggplot(mapping = aes(x = customer)) +
geom_line(mapping = aes(y = predict_reg)) +
facet_grid(~ hardest_customer$levels)
At higher levels of xn_01, there is a higher chance of predicting an event for Customer Other.